Image-Text-to-Text
GGUF
llama.cpp
rocm
amd
rocmfp4
rocmfpx
strix-halo
amd-strix-halo
gfx1151
ryzen-ai-max
ryzen-ai-max-395
radeon-8060s
Mixture of Experts
reasoning
multimodal
vision
nex
qwen3.5
quantized
conversational
Instructions to use kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF 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 kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF 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 kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0 # Run inference directly in the terminal: llama cli -hf kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0 # Run inference directly in the terminal: llama cli -hf kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_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 kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0 # Run inference directly in the terminal: ./llama-cli -hf kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_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 kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0
Use Docker
docker model run hf.co/kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0
- LM Studio
- Jan
- vLLM
How to use kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF", "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/kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0
- Ollama
How to use kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF with Ollama:
ollama run hf.co/kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0
- Unsloth Desktop
- Pi
How to use kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_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": "kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF with Docker Model Runner:
docker model run hf.co/kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0
- Lemonade
How to use kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0
Run and chat with the model
lemonade run user.Nex-N2.5-mini-ROCmFP4-GGUF-Q4_0
List all available models
lemonade list
- Hermes Agent
How to use kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_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 kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_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 "kingjones777/Nex-N2.5-mini-ROCmFP4-GGUF:Q4_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"
| 0.00.073.166 I common_init_result: fitting params to device memory ... | |
| 0.00.073.169 I common_init_result: (for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on) | |
| 0.00.618.000 W llama_model_loader: direct I/O is enabled, disabling mmap | |
| 0.01.632.328 W read_raw_unsafe: Falling back to buffered IO due to Bad address | |
| 0.21.360.980 W llama_context: n_ctx_seq (2048) < n_ctx_train (262144) -- the full capacity of the model will not be utilized | |
| 0.21.411.524 W common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable) | |
| 0.21.696.824 I | |
| 0.21.696.976 I system_info: n_threads = 16 (n_threads_batch = 16) / 32 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | FA_ALL_QUANTS = 1 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | | |
| 0.21.834.422 I kl_divergence: computing over 40 chunks, n_ctx=2048, batch_size=2048, n_seq=1 | |
| 0.25.227.075 I kl_divergence: 3.39 seconds per pass - ETA 2.25 minutes | |
| chunk PPL ln(PPL(Q)/PPL(base)) KL Divergence Δp RMS Same top p | |
| 1 6.1880 ± 0.4939 0.08329 ± 0.01978 0.13233 ± 0.00748 10.697 ± 0.585 % 86.022 ± 1.085 % | |
| 2 7.0357 ± 0.3926 0.05414 ± 0.01246 0.10961 ± 0.00433 9.075 ± 0.394 % 86.559 ± 0.754 % | |
| 3 7.4624 ± 0.3452 0.05947 ± 0.01021 0.11204 ± 0.00434 9.072 ± 0.327 % 86.250 ± 0.622 % | |
| 4 7.7345 ± 0.3193 0.05957 ± 0.00891 0.11467 ± 0.00464 9.213 ± 0.314 % 86.486 ± 0.535 % | |
| 5 7.5351 ± 0.2801 0.05356 ± 0.00785 0.11152 ± 0.00383 8.995 ± 0.270 % 86.667 ± 0.475 % | |
| 6 6.4595 ± 0.2123 0.04949 ± 0.00714 0.11027 ± 0.00353 9.495 ± 0.276 % 87.113 ± 0.428 % | |
| 7 5.9967 ± 0.1800 0.04378 ± 0.00691 0.12283 ± 0.00457 10.169 ± 0.285 % 87.250 ± 0.394 % | |
| 8 5.9141 ± 0.1649 0.04224 ± 0.00637 0.12112 ± 0.00408 10.053 ± 0.261 % 87.170 ± 0.370 % | |
| 9 6.2093 ± 0.1636 0.03840 ± 0.00600 0.12020 ± 0.00367 9.847 ± 0.240 % 86.825 ± 0.352 % | |
| 10 6.3404 ± 0.1596 0.04087 ± 0.00561 0.11641 ± 0.00333 9.682 ± 0.223 % 86.823 ± 0.334 % | |
| 11 6.4032 ± 0.1532 0.04194 ± 0.00528 0.11306 ± 0.00305 9.498 ± 0.210 % 86.795 ± 0.319 % | |
| 12 6.6610 ± 0.1540 0.04308 ± 0.00496 0.10959 ± 0.00281 9.281 ± 0.198 % 86.763 ± 0.306 % | |
| 13 6.6960 ± 0.1485 0.04143 ± 0.00472 0.10783 ± 0.00262 9.199 ± 0.188 % 86.773 ± 0.294 % | |
| 14 6.7584 ± 0.1443 0.04192 ± 0.00452 0.10607 ± 0.00245 9.074 ± 0.179 % 86.657 ± 0.284 % | |
| 15 6.8026 ± 0.1405 0.04223 ± 0.00435 0.10576 ± 0.00235 9.049 ± 0.171 % 86.660 ± 0.274 % | |
| 16 6.9572 ± 0.1392 0.03797 ± 0.00421 0.10524 ± 0.00223 8.990 ± 0.164 % 86.571 ± 0.267 % | |
| 17 7.0033 ± 0.1354 0.03762 ± 0.00406 0.10400 ± 0.00212 8.906 ± 0.157 % 86.522 ± 0.259 % | |
| 18 7.0947 ± 0.1334 0.03740 ± 0.00393 0.10350 ± 0.00202 8.881 ± 0.152 % 86.532 ± 0.252 % | |
| 19 7.0450 ± 0.1294 0.03728 ± 0.00382 0.10187 ± 0.00193 8.789 ± 0.147 % 86.639 ± 0.244 % | |
| 20 6.7808 ± 0.1206 0.03838 ± 0.00381 0.10695 ± 0.00193 9.167 ± 0.147 % 86.569 ± 0.238 % | |
| 21 6.8071 ± 0.1180 0.03975 ± 0.00374 0.10769 ± 0.00187 9.179 ± 0.142 % 86.506 ± 0.233 % | |
| 22 6.8328 ± 0.1159 0.04152 ± 0.00369 0.10920 ± 0.00187 9.217 ± 0.139 % 86.501 ± 0.228 % | |
| 23 6.8923 ± 0.1144 0.04279 ± 0.00360 0.10882 ± 0.00181 9.197 ± 0.137 % 86.498 ± 0.223 % | |
| 24 6.8910 ± 0.1117 0.04255 ± 0.00351 0.10896 ± 0.00176 9.191 ± 0.134 % 86.490 ± 0.218 % | |
| 25 6.9237 ± 0.1100 0.04257 ± 0.00344 0.10863 ± 0.00170 9.157 ± 0.130 % 86.424 ± 0.214 % | |
| 26 6.8938 ± 0.1073 0.04273 ± 0.00338 0.10952 ± 0.00170 9.229 ± 0.130 % 86.435 ± 0.210 % | |
| 27 7.0651 ± 0.1086 0.04294 ± 0.00331 0.10883 ± 0.00167 9.149 ± 0.127 % 86.452 ± 0.206 % | |
| 28 7.1473 ± 0.1082 0.04166 ± 0.00323 0.10759 ± 0.00162 9.083 ± 0.125 % 86.514 ± 0.202 % | |
| 29 7.1505 ± 0.1064 0.04295 ± 0.00318 0.10739 ± 0.00158 9.106 ± 0.123 % 86.517 ± 0.198 % | |
| 30 7.0929 ± 0.1035 0.04287 ± 0.00312 0.10706 ± 0.00153 9.094 ± 0.121 % 86.452 ± 0.195 % | |
| 31 6.9865 ± 0.1000 0.04226 ± 0.00306 0.10620 ± 0.00149 9.057 ± 0.118 % 86.573 ± 0.191 % | |
| 32 6.8731 ± 0.0966 0.04016 ± 0.00304 0.10897 ± 0.00167 9.204 ± 0.119 % 86.550 ± 0.189 % | |
| 33 6.8112 ± 0.0941 0.04100 ± 0.00300 0.10867 ± 0.00163 9.201 ± 0.117 % 86.561 ± 0.186 % | |
| 34 6.7925 ± 0.0922 0.04042 ± 0.00293 0.10760 ± 0.00159 9.133 ± 0.115 % 86.594 ± 0.183 % | |
| 35 6.8061 ± 0.0911 0.04061 ± 0.00287 0.10675 ± 0.00155 9.093 ± 0.113 % 86.655 ± 0.180 % | |
| 36 6.8188 ± 0.0901 0.03999 ± 0.00283 0.10633 ± 0.00151 9.056 ± 0.111 % 86.717 ± 0.177 % | |
| 37 6.7235 ± 0.0873 0.03971 ± 0.00278 0.10555 ± 0.00148 9.021 ± 0.109 % 86.753 ± 0.174 % | |
| 38 6.6468 ± 0.0849 0.03876 ± 0.00274 0.10510 ± 0.00145 9.019 ± 0.107 % 86.762 ± 0.172 % | |
| 39 6.5673 ± 0.0825 0.03906 ± 0.00270 0.10487 ± 0.00142 9.014 ± 0.105 % 86.773 ± 0.170 % | |
| 40 6.4745 ± 0.0799 0.03865 ± 0.00266 0.10441 ± 0.00139 9.030 ± 0.104 % 86.794 ± 0.167 % | |
| ====== Perplexity statistics ====== | |
| Mean PPL(Q) : 6.474466 ± 0.079947 | |
| Mean PPL(base) : 6.228979 ± 0.075322 | |
| Cor(ln(PPL(Q)), ln(PPL(base))): 97.64% | |
| Mean ln(PPL(Q)/PPL(base)) : 0.038654 ± 0.002665 | |
| Mean PPL(Q)/PPL(base) : 1.039410 ± 0.002770 | |
| Mean PPL(Q)-PPL(base) : 0.245487 ± 0.017468 | |
| ====== KL divergence statistics ====== | |
| Mean KLD: 0.104408 ± 0.001395 | |
| Maximum KLD: 16.437456 | |
| 99.9% KLD: 3.401226 | |
| 99.0% KLD: 0.899358 | |
| 95.0% KLD: 0.354356 | |
| 90.0% KLD: 0.226252 | |
| Median KLD: 0.048009 | |
| 10.0% KLD: 0.000697 | |
| 5.0% KLD: 0.000180 | |
| 1.0% KLD: -0.000044 | |
| 0.1% KLD: -0.000336 | |
| Minimum KLD: -0.000813 | |
| ====== Token probability statistics ====== | |
| Mean Δp: -0.202 ± 0.045 % | |
| Maximum Δp: 99.758% | |
| 99.9% Δp: 56.495% | |
| 99.0% Δp: 25.703% | |
| 95.0% Δp: 11.848% | |
| 90.0% Δp: 6.930% | |
| 75.0% Δp: 1.471% | |
| Median Δp: -0.001% | |
| 25.0% Δp: -1.409% | |
| 10.0% Δp: -7.175% | |
| 5.0% Δp: -13.010% | |
| 1.0% Δp: -31.209% | |
| 0.1% Δp: -69.269% | |
| Minimum Δp: -98.138% | |
| RMS Δp : 9.030 ± 0.104 % | |
| Same top p: 86.794 ± 0.167 % | |