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"
| 0.00.044.057 I common_init_result: fitting params to device memory ... | |
| 0.00.044.061 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) | |
| 0.00.458.402 W llama_model_loader: direct I/O is enabled, disabling mmap | |
| 0.01.547.350 W read_raw_unsafe: Falling back to buffered IO due to Bad address | |
| 0.29.871.824 W llama_context: n_ctx_seq (2048) < n_ctx_train (262144) -- the full capacity of the model will not be utilized | |
| 0.29.921.987 W common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable) | |
| 0.30.136.871 I | |
| 0.30.137.012 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 | | |
| 0.30.272.958 I kl_divergence: computing over 40 chunks, n_ctx=2048, batch_size=2048, n_seq=1 | |
| 0.33.203.394 I kl_divergence: 2.93 seconds per pass - ETA 1.95 minutes | |
| chunk PPL ln(PPL(Q)/PPL(base)) KL Divergence Δp RMS Same top p | |
| 1 5.9966 ± 0.4697 0.05187 ± 0.01811 0.11459 ± 0.00733 10.192 ± 0.639 % 86.217 ± 1.078 % | |
| 2 6.9326 ± 0.3865 0.03938 ± 0.01202 0.09983 ± 0.00427 8.906 ± 0.415 % 86.364 ± 0.759 % | |
| 3 7.4953 ± 0.3486 0.06386 ± 0.01034 0.10617 ± 0.00431 9.400 ± 0.398 % 86.771 ± 0.612 % | |
| 4 7.8932 ± 0.3295 0.07988 ± 0.00943 0.11534 ± 0.00606 9.599 ± 0.356 % 86.779 ± 0.530 % | |
| 5 7.6968 ± 0.2885 0.07479 ± 0.00839 0.11294 ± 0.00512 9.430 ± 0.323 % 86.979 ± 0.471 % | |
| 6 6.6156 ± 0.2191 0.07337 ± 0.00761 0.11303 ± 0.00469 10.110 ± 0.316 % 87.341 ± 0.424 % | |
| 7 6.1496 ± 0.1860 0.06895 ± 0.00729 0.12010 ± 0.00470 10.509 ± 0.310 % 87.544 ± 0.390 % | |
| 8 6.0524 ± 0.1698 0.06536 ± 0.00664 0.11729 ± 0.00419 10.338 ± 0.282 % 87.414 ± 0.367 % | |
| 9 6.3606 ± 0.1689 0.06248 ± 0.00621 0.11624 ± 0.00378 10.074 ± 0.260 % 87.053 ± 0.350 % | |
| 10 6.4785 ± 0.1643 0.06242 ± 0.00577 0.11173 ± 0.00343 9.809 ± 0.243 % 87.185 ± 0.330 % | |
| 11 6.5332 ± 0.1574 0.06204 ± 0.00542 0.10800 ± 0.00313 9.617 ± 0.228 % 87.203 ± 0.315 % | |
| 12 6.7836 ± 0.1577 0.06132 ± 0.00509 0.10489 ± 0.00288 9.401 ± 0.215 % 87.154 ± 0.302 % | |
| 13 6.8332 ± 0.1523 0.06171 ± 0.00483 0.10310 ± 0.00268 9.272 ± 0.203 % 87.112 ± 0.291 % | |
| 14 6.8837 ± 0.1476 0.06029 ± 0.00462 0.10108 ± 0.00251 9.107 ± 0.193 % 87.222 ± 0.279 % | |
| 15 6.9222 ± 0.1435 0.05966 ± 0.00443 0.10045 ± 0.00236 9.064 ± 0.184 % 87.129 ± 0.270 % | |
| 16 7.0981 ± 0.1428 0.05802 ± 0.00427 0.09952 ± 0.00223 8.947 ± 0.176 % 87.170 ± 0.261 % | |
| 17 7.1355 ± 0.1388 0.05632 ± 0.00410 0.09812 ± 0.00211 8.873 ± 0.170 % 87.229 ± 0.253 % | |
| 18 7.2233 ± 0.1366 0.05535 ± 0.00396 0.09744 ± 0.00201 8.809 ± 0.164 % 87.151 ± 0.247 % | |
| 19 7.1804 ± 0.1327 0.05631 ± 0.00385 0.09656 ± 0.00193 8.767 ± 0.160 % 87.138 ± 0.240 % | |
| 20 6.9267 ± 0.1241 0.05967 ± 0.00383 0.10094 ± 0.00190 9.066 ± 0.156 % 87.043 ± 0.235 % | |
| 21 6.9448 ± 0.1213 0.05978 ± 0.00374 0.10135 ± 0.00184 9.031 ± 0.151 % 87.032 ± 0.229 % | |
| 22 6.9675 ± 0.1190 0.06104 ± 0.00367 0.10256 ± 0.00183 9.077 ± 0.149 % 87.035 ± 0.224 % | |
| 23 7.0270 ± 0.1174 0.06214 ± 0.00359 0.10236 ± 0.00177 9.057 ± 0.146 % 86.986 ± 0.219 % | |
| 24 7.0192 ± 0.1145 0.06099 ± 0.00349 0.10191 ± 0.00171 9.016 ± 0.143 % 86.983 ± 0.215 % | |
| 25 7.0530 ± 0.1127 0.06108 ± 0.00342 0.10141 ± 0.00166 8.977 ± 0.139 % 86.952 ± 0.211 % | |
| 26 7.0192 ± 0.1099 0.06075 ± 0.00334 0.10143 ± 0.00162 8.999 ± 0.137 % 86.973 ± 0.206 % | |
| 27 7.1950 ± 0.1112 0.06116 ± 0.00329 0.10126 ± 0.00160 8.943 ± 0.134 % 86.988 ± 0.202 % | |
| 28 7.2801 ± 0.1108 0.06006 ± 0.00321 0.10017 ± 0.00155 8.860 ± 0.131 % 86.975 ± 0.199 % | |
| 29 7.2833 ± 0.1089 0.06136 ± 0.00316 0.10033 ± 0.00152 8.904 ± 0.130 % 86.925 ± 0.196 % | |
| 30 7.2262 ± 0.1061 0.06148 ± 0.00310 0.09994 ± 0.00148 8.892 ± 0.127 % 86.937 ± 0.192 % | |
| 31 7.1166 ± 0.1024 0.06072 ± 0.00302 0.09878 ± 0.00144 8.837 ± 0.124 % 87.043 ± 0.189 % | |
| 32 7.0141 ± 0.0992 0.06047 ± 0.00303 0.10174 ± 0.00161 9.036 ± 0.126 % 87.014 ± 0.186 % | |
| 33 6.9480 ± 0.0965 0.06088 ± 0.00298 0.10139 ± 0.00157 9.021 ± 0.124 % 87.046 ± 0.183 % | |
| 34 6.9248 ± 0.0946 0.05971 ± 0.00291 0.10041 ± 0.00152 8.964 ± 0.121 % 87.091 ± 0.180 % | |
| 35 6.9370 ± 0.0934 0.05965 ± 0.00285 0.09981 ± 0.00149 8.914 ± 0.119 % 87.139 ± 0.177 % | |
| 36 6.9569 ± 0.0925 0.06004 ± 0.00282 0.09978 ± 0.00146 8.900 ± 0.118 % 87.159 ± 0.174 % | |
| 37 6.8518 ± 0.0895 0.05860 ± 0.00276 0.09882 ± 0.00142 8.866 ± 0.115 % 87.192 ± 0.172 % | |
| 38 6.7745 ± 0.0870 0.05779 ± 0.00272 0.09818 ± 0.00139 8.852 ± 0.114 % 87.256 ± 0.169 % | |
| 39 6.6883 ± 0.0845 0.05732 ± 0.00267 0.09776 ± 0.00137 8.864 ± 0.112 % 87.232 ± 0.167 % | |
| 40 6.5921 ± 0.0819 0.05666 ± 0.00263 0.09716 ± 0.00134 8.853 ± 0.111 % 87.265 ± 0.165 % | |
| ====== Perplexity statistics ====== | |
| Mean PPL(Q) : 6.592123 ± 0.081874 | |
| Mean PPL(base) : 6.228979 ± 0.075322 | |
| Cor(ln(PPL(Q)), ln(PPL(base))): 97.73% | |
| Mean ln(PPL(Q)/PPL(base)) : 0.056663 ± 0.002630 | |
| Mean PPL(Q)/PPL(base) : 1.058299 ± 0.002783 | |
| Mean PPL(Q)-PPL(base) : 0.363144 ± 0.017958 | |
| ====== KL divergence statistics ====== | |
| Mean KLD: 0.097165 ± 0.001337 | |
| Maximum KLD: 15.969161 | |
| 99.9% KLD: 3.145117 | |
| 99.0% KLD: 0.858566 | |
| 95.0% KLD: 0.329361 | |
| 90.0% KLD: 0.207554 | |
| Median KLD: 0.043968 | |
| 10.0% KLD: 0.000631 | |
| 5.0% KLD: 0.000159 | |
| 1.0% KLD: -0.000029 | |
| 0.1% KLD: -0.000286 | |
| Minimum KLD: -0.000564 | |
| ====== Token probability statistics ====== | |
| Mean Δp: -0.372 ± 0.044 % | |
| Maximum Δp: 98.904% | |
| 99.9% Δp: 55.573% | |
| 99.0% Δp: 23.490% | |
| 95.0% Δp: 10.880% | |
| 90.0% Δp: 6.394% | |
| 75.0% Δp: 1.299% | |
| Median Δp: -0.005% | |
| 25.0% Δp: -1.458% | |
| 10.0% Δp: -7.029% | |
| 5.0% Δp: -12.485% | |
| 1.0% Δp: -31.169% | |
| 0.1% Δp: -73.630% | |
| Minimum Δp: -99.736% | |
| RMS Δp : 8.853 ± 0.111 % | |
| Same top p: 87.265 ± 0.165 % | |