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"
| { | |
| "completed_at": 1789608195.1082451, | |
| "build": "final-all-v1-pm4", | |
| "protocol": "HumanEval0-9 canonical prompts in retained local non-thinking greedy chat adapter; served MTP3, full262144 allocation, one first trajectory per task, natural EOS", | |
| "weighted_decode_tokens_per_second": 60.35102655869076, | |
| "minimum_case_tps": 56.09397436570597, | |
| "maximum_case_tps": 64.76202653665553, | |
| "generated_tokens": 1633, | |
| "timed_decode_tokens": 1623, | |
| "decode_seconds": 26.892666, | |
| "summed_request_seconds": 36.057379722595215, | |
| "drafted_tokens": 1260.0, | |
| "accepted_tokens": 1221.0, | |
| "acceptance_fraction": 0.969047619047619, | |
| "valid_tasks": 10, | |
| "quality_score_claim": false, | |
| "fresh_prompt_cache_all_tasks": true, | |
| "sqlite_rows_verified": 10, | |
| "persistence_note": "Task0 completed in the first load; its metadata serialization failed after the full response and JSONL were saved. Corrected only command serialization, imported the original result, then generated tasks1-9 in a second identical load. No task was regenerated. The saved panel-resume panel_elapsed_seconds covers that resumed phase only; summed request/decode times include all10 tasks.", | |
| "rows": [ | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 56.09397436570597, | |
| "decode_seconds": 3.066283, | |
| "decode_timed_tokens": 172, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 134, | |
| "generated_tokens": 173, | |
| "total_tokens": 307, | |
| "request_wall_seconds": 4.12631893157959, | |
| "ttfp_ms": 1057.2734710294753, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 173, | |
| "tokens_evaluated": 134, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T011851Z-final-all-v1-pm4-HumanEval-0-api.raw", | |
| "task": "HumanEval/0", | |
| "recorder_exit": 1, | |
| "persistence_recovered": true, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel/HumanEval-0/row-recovered.json", | |
| "drafted_tokens": 135, | |
| "accepted_tokens": 129 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 64.36654266122495, | |
| "decode_seconds": 3.588821, | |
| "decode_timed_tokens": 231, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 126, | |
| "generated_tokens": 232, | |
| "total_tokens": 358, | |
| "request_wall_seconds": 5.121450185775757, | |
| "ttfp_ms": 1530.2266778890043, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 232, | |
| "tokens_evaluated": 126, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012137Z-final-all-v1-pm4-HumanEval-1-api.raw", | |
| "task": "HumanEval/1", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-1/row.json", | |
| "drafted_tokens": 177.0, | |
| "accepted_tokens": 174.0 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 63.59207801688104, | |
| "decode_seconds": 1.509622, | |
| "decode_timed_tokens": 96, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 95, | |
| "generated_tokens": 97, | |
| "total_tokens": 192, | |
| "request_wall_seconds": 2.163600444793701, | |
| "ttfp_ms": 651.7064250074327, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 97, | |
| "tokens_evaluated": 95, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012142Z-final-all-v1-pm4-HumanEval-2-api.raw", | |
| "task": "HumanEval/2", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-2/row.json", | |
| "drafted_tokens": 75.0, | |
| "accepted_tokens": 74.0 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 64.76202653665553, | |
| "decode_seconds": 2.408819, | |
| "decode_timed_tokens": 156, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 129, | |
| "generated_tokens": 157, | |
| "total_tokens": 286, | |
| "request_wall_seconds": 3.3317527770996094, | |
| "ttfp_ms": 921.4452710002661, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 157, | |
| "tokens_evaluated": 129, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012144Z-final-all-v1-pm4-HumanEval-3-api.raw", | |
| "task": "HumanEval/3", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-3/row.json", | |
| "drafted_tokens": 120.0, | |
| "accepted_tokens": 117.0 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 62.50495295944211, | |
| "decode_seconds": 2.6877869999999997, | |
| "decode_timed_tokens": 168, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 128, | |
| "generated_tokens": 169, | |
| "total_tokens": 297, | |
| "request_wall_seconds": 3.5662331581115723, | |
| "ttfp_ms": 875.4782220348716, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 169, | |
| "tokens_evaluated": 128, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012148Z-final-all-v1-pm4-HumanEval-4-api.raw", | |
| "task": "HumanEval/4", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-4/row.json", | |
| "drafted_tokens": 129.0, | |
| "accepted_tokens": 126.0 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 57.36296811743736, | |
| "decode_seconds": 2.6672260000000003, | |
| "decode_timed_tokens": 153, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 104, | |
| "generated_tokens": 154, | |
| "total_tokens": 258, | |
| "request_wall_seconds": 3.430769920349121, | |
| "ttfp_ms": 761.1340200528502, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 154, | |
| "tokens_evaluated": 104, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012151Z-final-all-v1-pm4-HumanEval-5-api.raw", | |
| "task": "HumanEval/5", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-5/row.json", | |
| "drafted_tokens": 123.0, | |
| "accepted_tokens": 115.0 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 58.35354247096843, | |
| "decode_seconds": 3.650164, | |
| "decode_timed_tokens": 213, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 124, | |
| "generated_tokens": 214, | |
| "total_tokens": 338, | |
| "request_wall_seconds": 4.545674085617065, | |
| "ttfp_ms": 893.1537920143455, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 214, | |
| "tokens_evaluated": 124, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012155Z-final-all-v1-pm4-HumanEval-6-api.raw", | |
| "task": "HumanEval/6", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-6/row.json", | |
| "drafted_tokens": 168.0, | |
| "accepted_tokens": 160.0 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 59.95297742149265, | |
| "decode_seconds": 1.851451, | |
| "decode_timed_tokens": 111, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 104, | |
| "generated_tokens": 112, | |
| "total_tokens": 216, | |
| "request_wall_seconds": 2.6149725914001465, | |
| "ttfp_ms": 761.6006780881435, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 112, | |
| "tokens_evaluated": 104, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012200Z-final-all-v1-pm4-HumanEval-7-api.raw", | |
| "task": "HumanEval/7", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-7/row.json", | |
| "drafted_tokens": 84.0, | |
| "accepted_tokens": 83.0 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 59.57582016045754, | |
| "decode_seconds": 2.719224, | |
| "decode_timed_tokens": 162, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 126, | |
| "generated_tokens": 163, | |
| "total_tokens": 289, | |
| "request_wall_seconds": 3.6378886699676514, | |
| "ttfp_ms": 915.6202138401568, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 163, | |
| "tokens_evaluated": 126, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012202Z-final-all-v1-pm4-HumanEval-8-api.raw", | |
| "task": "HumanEval/8", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-8/row.json", | |
| "drafted_tokens": 123.0, | |
| "accepted_tokens": 122.0 | |
| }, | |
| { | |
| "status": "complete", | |
| "valid_speed_case": true, | |
| "native_tg": 58.68910413087452, | |
| "decode_seconds": 2.7432689999999997, | |
| "decode_timed_tokens": 161, | |
| "native_counting": "generated-minus-one", | |
| "prompt_tokens": 110, | |
| "generated_tokens": 162, | |
| "total_tokens": 272, | |
| "request_wall_seconds": 3.518718957901001, | |
| "ttfp_ms": 773.098937002942, | |
| "reasoning_block_detected": false, | |
| "finish": { | |
| "stop": true, | |
| "tokens_predicted": 162, | |
| "tokens_evaluated": 110, | |
| "truncated": false, | |
| "stop_type": "eos", | |
| "stopping_word": "" | |
| }, | |
| "error": null, | |
| "raw_output": "/home/halo/bench-results/llama/20260917T012206Z-final-all-v1-pm4-HumanEval-9-api.raw", | |
| "task": "HumanEval/9", | |
| "recorder_exit": 0, | |
| "row": "/home/halo/flash-combined-20260916/humaneval-decode-20260917/panel-resume/HumanEval-9/row.json", | |
| "drafted_tokens": 126.0, | |
| "accepted_tokens": 121.0 | |
| } | |
| ] | |
| } | |