Image-Text-to-Text
GGUF
llama.cpp
qwen
qwen3.8
qwen3.8-flash-next
amd
rocm
gfx1151
ryzen-ai-max-395
strix-halo
mixture-of-experts
iu4
mtp
speculative-decoding
nvme
ple
long-context
local-inference
vision
conversational
Instructions to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0 # Run inference directly in the terminal: llama cli -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0 # Run inference directly in the terminal: llama cli -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Use Docker
docker model run hf.co/jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
- LM Studio
- Jan
- vLLM
How to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
- Ollama
How to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with Ollama:
ollama run hf.co/jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
- Unsloth Desktop
- Pi
How to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with Docker Model Runner:
docker model run hf.co/jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
- Lemonade
How to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Run and chat with the model
lemonade run user.Qwen3.8-Flash-CIRU-STRIX-IU4-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4:Q8_0" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
| { | |
| "status": "COMPLETE", | |
| "created_at": "2026-09-05T15:08:13.269354+00:00", | |
| "host": "sozo", | |
| "arms": [ | |
| "ciru", | |
| "agention", | |
| "unsloth" | |
| ], | |
| "mtp_off_sweep": { | |
| "ciru": [ | |
| { | |
| "prompt_tokens": 512, | |
| "generated_tokens": 128, | |
| "pp": 306.5260717785876, | |
| "tg": 22.54527250488629, | |
| "ttfp_ms": 1671.9896793365479, | |
| "total_ms": 7305.761814117432, | |
| "memory": { | |
| "delta_gtt_used_bytes": 0, | |
| "delta_ram_used_bytes": 745472, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89918681088, | |
| "ram_available_bytes": 40144433152, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94165233664, | |
| "t": 1788619776.7673035, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 168734720 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89918681088, | |
| "ram_available_bytes": 40146853888, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94162812928, | |
| "t": 1788619784.0726674, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 168734720 | |
| }, | |
| "peak_gtt_used_bytes": 89918681088, | |
| "peak_ram_used_bytes": 94165979136, | |
| "peak_vram_used_bytes": 168734720, | |
| "sample_count": 31 | |
| }, | |
| "source_row_sha256": "473fb0da15e39b5a83b5bb67c70bbc5aeb83a00e93786a907b7eb88739d14b1b", | |
| "source_raw_sha256": "e7185d638e0c37bd72c9ad349a8adadf35b7ed369e269d17b5985691619816a6", | |
| "label": "v2-ciru-rc2-no-mtp-pp512" | |
| }, | |
| { | |
| "prompt_tokens": 2048, | |
| "generated_tokens": 128, | |
| "pp": 382.0255487047133, | |
| "tg": 20.942985114154936, | |
| "ttfp_ms": 5364.029407501221, | |
| "total_ms": 11428.162574768066, | |
| "memory": { | |
| "delta_gtt_used_bytes": 393216, | |
| "delta_ram_used_bytes": 235118592, | |
| "delta_vram_used_bytes": 344064, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89918681088, | |
| "ram_available_bytes": 40143777792, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94165889024, | |
| "t": 1788619784.1546354, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 168734720 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89919074304, | |
| "ram_available_bytes": 39909175296, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94400491520, | |
| "t": 1788619795.5826085, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169078784 | |
| }, | |
| "peak_gtt_used_bytes": 89919074304, | |
| "peak_ram_used_bytes": 94401007616, | |
| "peak_vram_used_bytes": 169078784, | |
| "sample_count": 47 | |
| }, | |
| "source_row_sha256": "bd259a73f6cd69f048c4269908915d19c26a1debd395f507e9631fe1bb3d44a8", | |
| "source_raw_sha256": "a9ccac0bd0ebbcaf5c28d926d1881d1d30adbba564d1057bfc306983ef4bf5ec", | |
| "label": "v2-ciru-rc2-no-mtp-pp2048" | |
| }, | |
| { | |
| "prompt_tokens": 8192, | |
| "generated_tokens": 128, | |
| "pp": 370.40756452549965, | |
| "tg": 19.19183920684209, | |
| "ttfp_ms": 22118.80850791931, | |
| "total_ms": 28736.945390701294, | |
| "memory": { | |
| "delta_gtt_used_bytes": 229376, | |
| "delta_ram_used_bytes": 470446080, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89919074304, | |
| "ram_available_bytes": 40156749824, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94152916992, | |
| "t": 1788619795.701831, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169078784 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89919303680, | |
| "ram_available_bytes": 39686303744, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94623363072, | |
| "t": 1788619824.4386148, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169078784 | |
| }, | |
| "peak_gtt_used_bytes": 89919303680, | |
| "peak_ram_used_bytes": 94623363072, | |
| "peak_vram_used_bytes": 169078784, | |
| "sample_count": 116 | |
| }, | |
| "source_row_sha256": "da000c4648ae584c75dbc4336187587ee55e69de74bb8acd31a44ccfac4e9c72", | |
| "source_raw_sha256": "004a8ef9965ca1c6548f1ead1dc8dcb46e699d5e683ca5a6e5a4f3d5fab5b76b", | |
| "label": "v2-ciru-rc2-no-mtp-pp8192" | |
| }, | |
| { | |
| "prompt_tokens": 16384, | |
| "generated_tokens": 128, | |
| "pp": 352.1295823107842, | |
| "tg": 17.472675212409946, | |
| "ttfp_ms": 46532.26041793823, | |
| "total_ms": 53801.73420906067, | |
| "memory": { | |
| "delta_gtt_used_bytes": 0, | |
| "delta_ram_used_bytes": 553902080, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89919303680, | |
| "ram_available_bytes": 39922704384, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94386962432, | |
| "t": 1788619824.5504465, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169078784 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89919303680, | |
| "ram_available_bytes": 39378653184, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94931013632, | |
| "t": 1788619878.3519537, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169058304 | |
| }, | |
| "peak_gtt_used_bytes": 89919303680, | |
| "peak_ram_used_bytes": 94940864512, | |
| "peak_vram_used_bytes": 169078784, | |
| "sample_count": 216 | |
| }, | |
| "source_row_sha256": "6f23c195db77cb88ddc4731f3981eec2d0ddb02db483eda3dc574cc78c9f2467", | |
| "source_raw_sha256": "4904535ad05beae3366bd04f815587b01a5926a930809fc9dbfefb62d974c152", | |
| "label": "v2-ciru-rc2-no-mtp-pp16384" | |
| }, | |
| { | |
| "prompt_tokens": 32768, | |
| "generated_tokens": 128, | |
| "pp": 321.33055955606176, | |
| "tg": 14.323446658864336, | |
| "ttfp_ms": 101982.33151435852, | |
| "total_ms": 110850.14271736145, | |
| "memory": { | |
| "delta_gtt_used_bytes": 0, | |
| "delta_ram_used_bytes": 329519104, | |
| "delta_vram_used_bytes": 8192, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89919303680, | |
| "ram_available_bytes": 39596859392, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94712807424, | |
| "t": 1788619878.4932935, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169058304 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89919303680, | |
| "ram_available_bytes": 39267360768, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 95042306048, | |
| "t": 1788619989.3432505, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169062400 | |
| }, | |
| "peak_gtt_used_bytes": 89919303680, | |
| "peak_ram_used_bytes": 95042326528, | |
| "peak_vram_used_bytes": 169066496, | |
| "sample_count": 444 | |
| }, | |
| "source_row_sha256": "086960f2abb3b29f56ffffb3693a5243e423fd08be8c933516b9f12c174e2b5c", | |
| "source_raw_sha256": "acb5b3fb6f76b31c31ca6a42cb3674ece7373254a82754fb4ecc534b193d6e4d", | |
| "label": "v2-ciru-rc2-no-mtp-pp32768" | |
| }, | |
| { | |
| "prompt_tokens": 65536, | |
| "generated_tokens": 128, | |
| "pp": 282.9922226883487, | |
| "tg": 10.165215161986707, | |
| "ttfp_ms": 231594.47526931763, | |
| "total_ms": 244090.87371826172, | |
| "memory": { | |
| "delta_gtt_used_bytes": 52428800, | |
| "delta_ram_used_bytes": 601722880, | |
| "delta_vram_used_bytes": 40960, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89919303680, | |
| "ram_available_bytes": 39502532608, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 94807134208, | |
| "t": 1788619989.5020185, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169062400 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89971732480, | |
| "ram_available_bytes": 38902194176, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 95407472640, | |
| "t": 1788620233.5926564, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169103360 | |
| }, | |
| "peak_gtt_used_bytes": 89971732480, | |
| "peak_ram_used_bytes": 95408857088, | |
| "peak_vram_used_bytes": 169103360, | |
| "sample_count": 976 | |
| }, | |
| "source_row_sha256": "803b8e4cf5a82d1ae7ccc12fb1556dab4bf3ceb6e00aff90dcad2d8fbd04cb97", | |
| "source_raw_sha256": "ac7bfde237162b53d1d57f2a58aaefaa791d467566cba0fe7e270338724cbe2a", | |
| "label": "v2-ciru-rc2-no-mtp-pp65536" | |
| }, | |
| { | |
| "prompt_tokens": 131072, | |
| "generated_tokens": 128, | |
| "pp": 232.95215096846331, | |
| "tg": 6.748802247021679, | |
| "ttfp_ms": 562672.7845668793, | |
| "total_ms": 581497.358083725, | |
| "memory": { | |
| "delta_gtt_used_bytes": 35651584, | |
| "delta_ram_used_bytes": 1520336896, | |
| "delta_vram_used_bytes": 8192, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 89971732480, | |
| "ram_available_bytes": 39124025344, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 95185641472, | |
| "t": 1788620233.7813432, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169103360 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 90007384064, | |
| "ram_available_bytes": 37603688448, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 96705978368, | |
| "t": 1788620815.2784042, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 169111552 | |
| }, | |
| "peak_gtt_used_bytes": 90007384064, | |
| "peak_ram_used_bytes": 96705978368, | |
| "peak_vram_used_bytes": 169111552, | |
| "sample_count": 2324 | |
| }, | |
| "source_row_sha256": "a7566b16fdc3740f078a69e74e558ae6b548c8624a799308da02447ec0427fcf", | |
| "source_raw_sha256": "6bc32148916d08c2feee98b09be62b36bad843f1df5eab9bf702dd6c1336ec5a", | |
| "label": "v2-ciru-rc2-no-mtp-pp131072" | |
| } | |
| ], | |
| "agention": [ | |
| { | |
| "prompt_tokens": 512, | |
| "generated_tokens": 128, | |
| "pp": 357.62781003257766, | |
| "tg": 25.932868583656983, | |
| "ttfp_ms": 1433.5122108459473, | |
| "total_ms": 6331.249713897705, | |
| "memory": { | |
| "delta_gtt_used_bytes": 29687808, | |
| "delta_ram_used_bytes": 162824192, | |
| "delta_vram_used_bytes": 8192, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101335601152, | |
| "ram_available_bytes": 29871378432, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104438288384, | |
| "t": 1788581822.0923114, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 524312576 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101365288960, | |
| "ram_available_bytes": 29708554240, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104601112576, | |
| "t": 1788581828.4232647, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 524320768 | |
| }, | |
| "peak_gtt_used_bytes": 101365288960, | |
| "peak_ram_used_bytes": 104601112576, | |
| "peak_vram_used_bytes": 524320768, | |
| "sample_count": 27 | |
| }, | |
| "source_row_sha256": "775a400e7c22fa92d91edf847405c2c51a0ed18661efe85a8fd6255a99bc6086", | |
| "source_raw_sha256": "6febe5d187916fe64790b491cc456c7dadc432d26f2ffc9916e987dba8c8620b", | |
| "label": "agention-card-ladder-pp512" | |
| }, | |
| { | |
| "prompt_tokens": 2048, | |
| "generated_tokens": 128, | |
| "pp": 363.83333235624184, | |
| "tg": 25.58463922435432, | |
| "ttfp_ms": 5631.121873855591, | |
| "total_ms": 10595.957040786743, | |
| "memory": { | |
| "delta_gtt_used_bytes": 4390912, | |
| "delta_ram_used_bytes": 243486720, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101365288960, | |
| "ram_available_bytes": 29818118144, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104491548672, | |
| "t": 1788581828.5312965, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 524320768 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29574631424, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104735035392, | |
| "t": 1788581839.1267073, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "peak_gtt_used_bytes": 101369679872, | |
| "peak_ram_used_bytes": 104735035392, | |
| "peak_vram_used_bytes": 524320768, | |
| "sample_count": 44 | |
| }, | |
| "source_row_sha256": "dadbba441f5daa39776c0bd59e0594e8cb76de2a4c98c1288687b0dcf45e66af", | |
| "source_raw_sha256": "b59f04d0ef7fbde95fb2a97a8004ca6b32dcdfa1834a5c75fcc77899cd7a3e24", | |
| "label": "agention-card-ladder-pp2048" | |
| }, | |
| { | |
| "prompt_tokens": 8192, | |
| "generated_tokens": 128, | |
| "pp": 325.5891187734956, | |
| "tg": 24.953315686558064, | |
| "ttfp_ms": 25164.159536361694, | |
| "total_ms": 30255.13529777527, | |
| "memory": { | |
| "delta_gtt_used_bytes": 0, | |
| "delta_ram_used_bytes": 233160704, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29795074048, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104514592768, | |
| "t": 1788581839.284278, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29561913344, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104747753472, | |
| "t": 1788581869.5386808, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "peak_gtt_used_bytes": 101369679872, | |
| "peak_ram_used_bytes": 104747753472, | |
| "peak_vram_used_bytes": 521228288, | |
| "sample_count": 122 | |
| }, | |
| "source_row_sha256": "102a59f7add6c625a184371d644d79a444d8f83387995f3735c1b49cad9c5447", | |
| "source_raw_sha256": "6c4d7d5185fefd323d4ee9896943a7223df04c4334454af249a111bec92b8c38", | |
| "label": "agention-card-ladder-pp8192" | |
| }, | |
| { | |
| "prompt_tokens": 16384, | |
| "generated_tokens": 128, | |
| "pp": 302.71994163181125, | |
| "tg": 24.35992382057209, | |
| "ttfp_ms": 54127.56133079529, | |
| "total_ms": 59342.663526535034, | |
| "memory": { | |
| "delta_gtt_used_bytes": 0, | |
| "delta_ram_used_bytes": 153559040, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29705891840, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104603774976, | |
| "t": 1788581869.7269146, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29552332800, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104757334016, | |
| "t": 1788581929.0693126, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "peak_gtt_used_bytes": 101369679872, | |
| "peak_ram_used_bytes": 104757334016, | |
| "peak_vram_used_bytes": 521228288, | |
| "sample_count": 238 | |
| }, | |
| "source_row_sha256": "41f2c620690cb08189ac49e3888386169ffecdd7b3275222f47d24078eb4face", | |
| "source_raw_sha256": "abdbb2b146e533e30b6e7ec9acfdc34d171529a5485d74e5ae389fa1ce6c41e7", | |
| "label": "agention-card-ladder-pp16384" | |
| }, | |
| { | |
| "prompt_tokens": 32768, | |
| "generated_tokens": 128, | |
| "pp": 273.9458158618122, | |
| "tg": 22.769845982610295, | |
| "ttfp_ms": 119622.07579612732, | |
| "total_ms": 125202.11839675903, | |
| "memory": { | |
| "delta_gtt_used_bytes": 0, | |
| "delta_ram_used_bytes": 247328768, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29789585408, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104520081408, | |
| "t": 1788581929.2211366, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29542256640, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104767410176, | |
| "t": 1788582054.4227529, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "peak_gtt_used_bytes": 101369679872, | |
| "peak_ram_used_bytes": 104767410176, | |
| "peak_vram_used_bytes": 521228288, | |
| "sample_count": 501 | |
| }, | |
| "source_row_sha256": "5a3b9729d7b3164e3a5e2400666207d03324c2a1285c32a2356ba325cc4b7219", | |
| "source_raw_sha256": "a88b8146341fa30fca8b8d3977f9fcafceca712cb89552e8bd2a6caed66acb60", | |
| "label": "agention-card-ladder-pp32768" | |
| }, | |
| { | |
| "prompt_tokens": 65536, | |
| "generated_tokens": 128, | |
| "pp": 229.67782088765648, | |
| "tg": 20.252305453882073, | |
| "ttfp_ms": 285350.79431533813, | |
| "total_ms": 291627.0384788513, | |
| "memory": { | |
| "delta_gtt_used_bytes": 0, | |
| "delta_ram_used_bytes": 193069056, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29699903488, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104609763328, | |
| "t": 1788582054.6204512, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29506834432, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104802832384, | |
| "t": 1788582346.2469826, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "peak_gtt_used_bytes": 101369679872, | |
| "peak_ram_used_bytes": 104802832384, | |
| "peak_vram_used_bytes": 521228288, | |
| "sample_count": 1164 | |
| }, | |
| "source_row_sha256": "f275968ad35f1d6554a1825f22ab7175558bc4f24fd555def9d0bcaeafd1a46f", | |
| "source_raw_sha256": "aadd44795c66555e4f3a7d730eb122b1cda5fb808e431081bc6371b244f3a3b0", | |
| "label": "agention-card-ladder-pp65536" | |
| }, | |
| { | |
| "prompt_tokens": 131072, | |
| "generated_tokens": 128, | |
| "pp": 184.33343093700745, | |
| "tg": 17.85921705754915, | |
| "ttfp_ms": 711083.1847190857, | |
| "total_ms": 718204.247713089, | |
| "memory": { | |
| "delta_gtt_used_bytes": 0, | |
| "delta_ram_used_bytes": 24977408, | |
| "delta_vram_used_bytes": 0, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 101369679872, | |
| "ram_available_bytes": 29738627072, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104571039744, | |
| "t": 1788582346.4750206, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 521228288 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 100378251264, | |
| "ram_available_bytes": 30736842752, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 103572824064, | |
| "t": 1788583064.6787124, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 516562944 | |
| }, | |
| "peak_gtt_used_bytes": 101369679872, | |
| "peak_ram_used_bytes": 104596017152, | |
| "peak_vram_used_bytes": 521228288, | |
| "sample_count": 2863 | |
| }, | |
| "source_row_sha256": "1dce28c2dca2dde22c874671a7f8507ba882fea2e31220c310e151b2ee7b5d02", | |
| "source_raw_sha256": "d4db4b5cfb6adbd5b4e0158910ece599ab7430d8f7b3a0002c014c095e18fd03", | |
| "label": "agention-card-ladder-pp131072" | |
| } | |
| ], | |
| "unsloth": [ | |
| { | |
| "prompt_tokens": 512, | |
| "generated_tokens": 128, | |
| "pp": 235.02841456808937, | |
| "tg": 24.53706574948274, | |
| "ttfp_ms": 2180.333137512207, | |
| "total_ms": 7356.932640075684, | |
| "memory": { | |
| "delta_gtt_used_bytes": 33128448, | |
| "delta_ram_used_bytes": 130293760, | |
| "delta_vram_used_bytes": 36864, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72547319808, | |
| "ram_available_bytes": 29520384000, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104789282816, | |
| "t": 1788585805.4317117, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 513044480 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72580448256, | |
| "ram_available_bytes": 29391036416, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104918630400, | |
| "t": 1788585812.7882414, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 513081344 | |
| }, | |
| "peak_gtt_used_bytes": 72580448256, | |
| "peak_ram_used_bytes": 104919576576, | |
| "peak_vram_used_bytes": 513081344, | |
| "sample_count": 31 | |
| }, | |
| "source_row_sha256": "ece8eca9f56e7d41b92246d1e12e6d97c871afa86a52c68dae0ab436b9486d61", | |
| "source_raw_sha256": "61734e4f1dc0c25ed4a7d31ff42632e8bed5c80998e076dd173f43a1defb97f8", | |
| "label": "unsloth-compare-unsloth-no-mtp-ladder-pp512" | |
| }, | |
| { | |
| "prompt_tokens": 2048, | |
| "generated_tokens": 128, | |
| "pp": 270.12154942142814, | |
| "tg": 23.98476457537146, | |
| "ttfp_ms": 7584.341049194336, | |
| "total_ms": 12880.511999130249, | |
| "memory": { | |
| "delta_gtt_used_bytes": 196608, | |
| "delta_ram_used_bytes": 214904832, | |
| "delta_vram_used_bytes": 61440, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72580448256, | |
| "ram_available_bytes": 29464027136, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104845639680, | |
| "t": 1788585812.9251993, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 513081344 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72580644864, | |
| "ram_available_bytes": 29274816512, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 105034850304, | |
| "t": 1788585825.8052313, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 513142784 | |
| }, | |
| "peak_gtt_used_bytes": 72580644864, | |
| "peak_ram_used_bytes": 105060544512, | |
| "peak_vram_used_bytes": 513142784, | |
| "sample_count": 53 | |
| }, | |
| "source_row_sha256": "d69332962298bd5ad08fab9a0e3fef4e16d9333c158bed8a76625af3d1925984", | |
| "source_raw_sha256": "b74560d0cf1b77f1b625051026746d3f6da653f00ae57c136eca7b695b480db7", | |
| "label": "unsloth-compare-unsloth-no-mtp-ladder-pp2048" | |
| }, | |
| { | |
| "prompt_tokens": 8192, | |
| "generated_tokens": 128, | |
| "pp": 274.78231585274597, | |
| "tg": 22.68762216927253, | |
| "ttfp_ms": 29816.16234779358, | |
| "total_ms": 35415.289640426636, | |
| "memory": { | |
| "delta_gtt_used_bytes": 15728640, | |
| "delta_ram_used_bytes": 230735872, | |
| "delta_vram_used_bytes": 12582912, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72580644864, | |
| "ram_available_bytes": 29519159296, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104790507520, | |
| "t": 1788585825.918342, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 513142784 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72580644864, | |
| "ram_available_bytes": 29288710144, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 105020956672, | |
| "t": 1788585861.333005, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 525725696 | |
| }, | |
| "peak_gtt_used_bytes": 72596373504, | |
| "peak_ram_used_bytes": 105021243392, | |
| "peak_vram_used_bytes": 525725696, | |
| "sample_count": 143 | |
| }, | |
| "source_row_sha256": "0ea4bddc406a4d9dc83ba3f0c0da273407a6ced581b5866e899479b310077b8c", | |
| "source_raw_sha256": "ab258b25a16756e808e1f88674c3b00bc5235d97e379fe8e2c139a5f08c75ada", | |
| "label": "unsloth-compare-unsloth-no-mtp-ladder-pp8192" | |
| }, | |
| { | |
| "prompt_tokens": 16384, | |
| "generated_tokens": 128, | |
| "pp": 266.86943792269767, | |
| "tg": 21.28038193426272, | |
| "ttfp_ms": 61398.22745323181, | |
| "total_ms": 67369.02523040771, | |
| "memory": { | |
| "delta_gtt_used_bytes": 33554432, | |
| "delta_ram_used_bytes": 207589376, | |
| "delta_vram_used_bytes": 2097152, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72580644864, | |
| "ram_available_bytes": 29452505088, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104857161728, | |
| "t": 1788585861.4517806, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 525725696 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72614199296, | |
| "ram_available_bytes": 29244940288, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 105064726528, | |
| "t": 1788585928.820109, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 508948480 | |
| }, | |
| "peak_gtt_used_bytes": 72614199296, | |
| "peak_ram_used_bytes": 105064751104, | |
| "peak_vram_used_bytes": 527822848, | |
| "sample_count": 270 | |
| }, | |
| "source_row_sha256": "b54e72f78ab5f0e40b37bea50c5e261557c25d435266a76b47dc8510e3448ee4", | |
| "source_raw_sha256": "025d8274176c18fb25e22b6b31ef0f5961169cfa52ac550ec2eb2bcbc601637f", | |
| "label": "unsloth-compare-unsloth-no-mtp-ladder-pp16384" | |
| }, | |
| { | |
| "prompt_tokens": 32768, | |
| "generated_tokens": 128, | |
| "pp": 254.67648015684492, | |
| "tg": 18.79396882302548, | |
| "ttfp_ms": 128672.66249656677, | |
| "total_ms": 135432.7266216278, | |
| "memory": { | |
| "delta_gtt_used_bytes": 33554432, | |
| "delta_ram_used_bytes": 275447808, | |
| "delta_vram_used_bytes": 4096, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72614199296, | |
| "ram_available_bytes": 29478772736, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104830894080, | |
| "t": 1788585928.9364839, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 508948480 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72647753728, | |
| "ram_available_bytes": 29203410944, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 105106255872, | |
| "t": 1788586064.368746, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 508948480 | |
| }, | |
| "peak_gtt_used_bytes": 72647753728, | |
| "peak_ram_used_bytes": 105106341888, | |
| "peak_vram_used_bytes": 508952576, | |
| "sample_count": 541 | |
| }, | |
| "source_row_sha256": "27587fba86adcf3881b1df1af6e172f39b6deec77cd2b9977407442ecb8f40df", | |
| "source_raw_sha256": "064cdb307d51d06fbfbc60eeb02c302e1a4977f03750f8c57ae6182c6042fdb1", | |
| "label": "unsloth-compare-unsloth-no-mtp-ladder-pp32768" | |
| }, | |
| { | |
| "prompt_tokens": 65536, | |
| "generated_tokens": 128, | |
| "pp": 228.77660940134743, | |
| "tg": 13.36603064357227, | |
| "ttfp_ms": 286475.9120941162, | |
| "total_ms": 295982.67555236816, | |
| "memory": { | |
| "delta_gtt_used_bytes": 67108864, | |
| "delta_ram_used_bytes": 57982976, | |
| "delta_vram_used_bytes": 8192, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72647753728, | |
| "ram_available_bytes": 29440012288, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104869654528, | |
| "t": 1788586064.5691152, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 508948480 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72714862592, | |
| "ram_available_bytes": 29507186688, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104802480128, | |
| "t": 1788586360.5511396, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 508952576 | |
| }, | |
| "peak_gtt_used_bytes": 72714862592, | |
| "peak_ram_used_bytes": 104927637504, | |
| "peak_vram_used_bytes": 508956672, | |
| "sample_count": 1180 | |
| }, | |
| "source_row_sha256": "511214805cfb1b70241842a3661094fcf41b4f6eea94d4536e2e5ed15b4241bb", | |
| "source_raw_sha256": "a484d183b8c22552f19a0a61b4147af35397a7dd58058ef5a7efda05cd904394", | |
| "label": "unsloth-compare-unsloth-no-mtp-ladder-pp65536" | |
| }, | |
| { | |
| "prompt_tokens": 131072, | |
| "generated_tokens": 128, | |
| "pp": 189.79235543145583, | |
| "tg": 9.978903654785249, | |
| "ttfp_ms": 690630.3057670593, | |
| "total_ms": 703363.6708259583, | |
| "memory": { | |
| "delta_gtt_used_bytes": 134217728, | |
| "delta_ram_used_bytes": 398831616, | |
| "delta_vram_used_bytes": 4096, | |
| "idle": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72714862592, | |
| "ram_available_bytes": 29736456192, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104573210624, | |
| "t": 1788586360.7821238, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 508952576 | |
| }, | |
| "last": { | |
| "gtt_total_bytes": 133143986176, | |
| "gtt_used_bytes": 72849080320, | |
| "ram_available_bytes": 29337624576, | |
| "ram_total_bytes": 134309666816, | |
| "ram_used_bytes": 104972042240, | |
| "t": 1788587064.145355, | |
| "vram_total_bytes": 536870912, | |
| "vram_used_bytes": 508952576 | |
| }, | |
| "peak_gtt_used_bytes": 72849080320, | |
| "peak_ram_used_bytes": 104972042240, | |
| "peak_vram_used_bytes": 508956672, | |
| "sample_count": 2803 | |
| }, | |
| "source_row_sha256": "5529d96e3d1bee14af87530c0a01105776fd9d9db50ddaae533838272c4b9839", | |
| "source_raw_sha256": "07d2d590b3972df5a6fbcf894d9c81fd331870e4d379c33ccea5ad45bb3ceb44", | |
| "label": "unsloth-compare-unsloth-no-mtp-ladder-pp131072" | |
| } | |
| ] | |
| }, | |
| "protocol_notes": [ | |
| "Seven sweep rows use the same cold native-token source fixture,128generated tokens,MTPoff and262144context. Runtime-specific cache and execution settings differ and remain in raw identities.", | |
| "No Unsloth-on-Laurent cross-run is included." | |
| ], | |
| "audit": { | |
| "verified_rows": 21, | |
| "mtp_off_rows": 21, | |
| "raw_and_sqlite_checks": "PASS", | |
| "fixture_sha256": "ca55a6b6f26a277bdf8c87ae9046f812253d6219d7f9e305075278b76a325e26" | |
| }, | |
| "host_notes": "All comparative speed rows: Sozo, Ryzen AI MAX+ 395 / Radeon 8060S gfx1151, 128 GiB shared memory, NixOS. No concurrent model workload. CIRU BF16 recaptured on Ciru, same hardware class; retained competitor BF16 captures on Sozo. Ubuntu build and GPU smoke on Ciru are separate qualification.", | |
| "labels": { | |
| "ciru": "CIRU ROCm10 RC2", | |
| "agention": "Agention FP4 FAST / Laurent", | |
| "unsloth": "Unsloth IQ4_XS / recommended fork" | |
| }, | |
| "memory_notes": "RAM is whole-system used memory from the official recorder, not process RSS. GTT and dedicated VRAM accounting overlap the shared-memory hardware and must not be summed. Idle, peak and deltas are retained per request.", | |
| "scope": "Three requested MTP-off context sweeps. Separately recorded native-thinking experiments are not part of this release comparison." | |
| } | |