Instructions to use guell00/VELUM-Coder 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 guell00/VELUM-Coder 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 guell00/VELUM-Coder:Q4_K_M # Run inference directly in the terminal: llama cli -hf guell00/VELUM-Coder:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf guell00/VELUM-Coder:Q4_K_M # Run inference directly in the terminal: llama cli -hf guell00/VELUM-Coder:Q4_K_M
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 guell00/VELUM-Coder:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf guell00/VELUM-Coder:Q4_K_M
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 guell00/VELUM-Coder:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf guell00/VELUM-Coder:Q4_K_M
Use Docker
docker model run hf.co/guell00/VELUM-Coder:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use guell00/VELUM-Coder with Ollama:
ollama run hf.co/guell00/VELUM-Coder:Q4_K_M
- Unsloth Studio
How to use guell00/VELUM-Coder with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for guell00/VELUM-Coder to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for guell00/VELUM-Coder to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for guell00/VELUM-Coder to start chatting
- Pi
How to use guell00/VELUM-Coder with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf guell00/VELUM-Coder:Q4_K_M
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": "guell00/VELUM-Coder:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use guell00/VELUM-Coder with Docker Model Runner:
docker model run hf.co/guell00/VELUM-Coder:Q4_K_M
- Lemonade
How to use guell00/VELUM-Coder with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull guell00/VELUM-Coder:Q4_K_M
Run and chat with the model
lemonade run user.VELUM-Coder-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use guell00/VELUM-Coder with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf guell00/VELUM-Coder:Q4_K_M
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 guell00/VELUM-Coder:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use guell00/VELUM-Coder with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf guell00/VELUM-Coder:Q4_K_M
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 "guell00/VELUM-Coder:Q4_K_M" \ --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"
Upload quantization_manifest.json
Browse files- quantization_manifest.json +248 -0
quantization_manifest.json
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"repo": "guell00/VELUM-Coder",
|
| 3 |
+
"base_model": "ornith-ai/Ornith-1.5-9B",
|
| 4 |
+
"dataset": "guell00/fds",
|
| 5 |
+
"source_model": "ornith_fds_recovered_ckpt250",
|
| 6 |
+
"llama_cpp_commit": "f280b26983ad0fdb705a0d9ebf0503e76f2899b0",
|
| 7 |
+
"generated_at": "2026-08-25T00:52:58.279253+00:00",
|
| 8 |
+
"imatrix": "imatrix/VELUM-Coder-imatrix.gguf",
|
| 9 |
+
"policy": {
|
| 10 |
+
"q8_uses_imatrix": false,
|
| 11 |
+
"q4_q3_q2_q1_use_imatrix": true,
|
| 12 |
+
"q5_q6_generated": false,
|
| 13 |
+
"iq1_m_embedding_type": "Q8_0",
|
| 14 |
+
"iq1_m_output_type": "Q8_0"
|
| 15 |
+
},
|
| 16 |
+
"quantizations": [
|
| 17 |
+
{
|
| 18 |
+
"name": "Q8_0",
|
| 19 |
+
"type": "Q8_0",
|
| 20 |
+
"imatrix": false,
|
| 21 |
+
"protected": false,
|
| 22 |
+
"note": "Highest-quality quantized build; intentionally no imatrix.",
|
| 23 |
+
"file": "VELUM-Coder-Q8_0.gguf",
|
| 24 |
+
"size_gb": 8.873176723718643,
|
| 25 |
+
"status": "uploaded"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"name": "Q4_K_M",
|
| 29 |
+
"type": "Q4_K_M",
|
| 30 |
+
"imatrix": true,
|
| 31 |
+
"protected": false,
|
| 32 |
+
"note": "Recommended default Q4.",
|
| 33 |
+
"file": "VELUM-Coder-Q4_K_M.gguf",
|
| 34 |
+
"size_gb": 5.242515951395035,
|
| 35 |
+
"status": "uploaded"
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"name": "Q4_K_S",
|
| 39 |
+
"type": "Q4_K_S",
|
| 40 |
+
"imatrix": true,
|
| 41 |
+
"protected": false,
|
| 42 |
+
"note": "Smaller Q4 K-quant.",
|
| 43 |
+
"file": "VELUM-Coder-Q4_K_S.gguf",
|
| 44 |
+
"size_gb": 4.984093099832535,
|
| 45 |
+
"status": "uploaded"
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"name": "IQ4_XS",
|
| 49 |
+
"type": "IQ4_XS",
|
| 50 |
+
"imatrix": true,
|
| 51 |
+
"protected": false,
|
| 52 |
+
"note": "Compact 4-bit I-Quant.",
|
| 53 |
+
"file": "VELUM-Coder-IQ4_XS.gguf",
|
| 54 |
+
"size_gb": 4.839561849832535,
|
| 55 |
+
"status": "uploaded"
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"name": "IQ4_NL",
|
| 59 |
+
"type": "IQ4_NL",
|
| 60 |
+
"imatrix": true,
|
| 61 |
+
"protected": false,
|
| 62 |
+
"note": "Non-linear 4-bit I-Quant.",
|
| 63 |
+
"file": "VELUM-Coder-IQ4_NL.gguf",
|
| 64 |
+
"size_gb": 5.046104818582535,
|
| 65 |
+
"status": "uploaded"
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"name": "Q4_1",
|
| 69 |
+
"type": "Q4_1",
|
| 70 |
+
"imatrix": true,
|
| 71 |
+
"protected": false,
|
| 72 |
+
"note": "Legacy Q4 variant.",
|
| 73 |
+
"file": "VELUM-Coder-Q4_1.gguf",
|
| 74 |
+
"size_gb": 5.410362631082535,
|
| 75 |
+
"status": "uploaded"
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"name": "Q4_0",
|
| 79 |
+
"type": "Q4_0",
|
| 80 |
+
"imatrix": true,
|
| 81 |
+
"protected": false,
|
| 82 |
+
"note": "Legacy compact Q4.",
|
| 83 |
+
"file": "VELUM-Coder-Q4_0.gguf",
|
| 84 |
+
"size_gb": 4.960167318582535,
|
| 85 |
+
"status": "uploaded"
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"name": "Q3_K_L",
|
| 89 |
+
"type": "Q3_K_L",
|
| 90 |
+
"imatrix": true,
|
| 91 |
+
"protected": false,
|
| 92 |
+
"note": "Largest Q3 K-quant.",
|
| 93 |
+
"file": "VELUM-Coder-Q3_K_L.gguf",
|
| 94 |
+
"size_gb": 4.587242513895035,
|
| 95 |
+
"status": "uploaded"
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"name": "Q3_K_M",
|
| 99 |
+
"type": "Q3_K_M",
|
| 100 |
+
"imatrix": true,
|
| 101 |
+
"protected": false,
|
| 102 |
+
"note": "Balanced Q3 K-quant.",
|
| 103 |
+
"file": "VELUM-Coder-Q3_K_M.gguf",
|
| 104 |
+
"size_gb": 4.305992513895035,
|
| 105 |
+
"status": "uploaded"
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"name": "Q3_K_S",
|
| 109 |
+
"type": "Q3_K_S",
|
| 110 |
+
"imatrix": true,
|
| 111 |
+
"protected": false,
|
| 112 |
+
"note": "Smaller Q3 K-quant.",
|
| 113 |
+
"file": "VELUM-Coder-Q3_K_S.gguf",
|
| 114 |
+
"size_gb": 3.966881185770035,
|
| 115 |
+
"status": "uploaded"
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"name": "IQ3_M",
|
| 119 |
+
"type": "IQ3_M",
|
| 120 |
+
"imatrix": true,
|
| 121 |
+
"protected": false,
|
| 122 |
+
"note": "Medium 3-bit I-Quant.",
|
| 123 |
+
"file": "VELUM-Coder-IQ3_M.gguf",
|
| 124 |
+
"size_gb": 4.112144857645035,
|
| 125 |
+
"status": "uploaded"
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"name": "IQ3_S",
|
| 129 |
+
"type": "IQ3_S",
|
| 130 |
+
"imatrix": true,
|
| 131 |
+
"protected": false,
|
| 132 |
+
"note": "Small 3-bit I-Quant.",
|
| 133 |
+
"file": "VELUM-Coder-IQ3_S.gguf",
|
| 134 |
+
"size_gb": 4.070640951395035,
|
| 135 |
+
"status": "uploaded"
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"name": "IQ3_XS",
|
| 139 |
+
"type": "IQ3_XS",
|
| 140 |
+
"imatrix": true,
|
| 141 |
+
"protected": false,
|
| 142 |
+
"note": "Extra-small 3-bit I-Quant.",
|
| 143 |
+
"file": "VELUM-Coder-IQ3_XS.gguf",
|
| 144 |
+
"size_gb": 3.951988607645035,
|
| 145 |
+
"status": "uploaded"
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"name": "IQ3_XXS",
|
| 149 |
+
"type": "IQ3_XXS",
|
| 150 |
+
"imatrix": true,
|
| 151 |
+
"protected": false,
|
| 152 |
+
"note": "Extremely compact 3-bit I-Quant.",
|
| 153 |
+
"file": "VELUM-Coder-IQ3_XXS.gguf",
|
| 154 |
+
"size_gb": 3.6677021086215973,
|
| 155 |
+
"status": "uploaded"
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"name": "Q2_K",
|
| 159 |
+
"type": "Q2_K",
|
| 160 |
+
"imatrix": true,
|
| 161 |
+
"protected": false,
|
| 162 |
+
"note": "Aggressive Q2 K-quant.",
|
| 163 |
+
"file": "VELUM-Coder-Q2_K.gguf",
|
| 164 |
+
"size_gb": 3.564415365457535,
|
| 165 |
+
"status": "uploaded"
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"name": "Q2_K_S",
|
| 169 |
+
"type": "Q2_K_S",
|
| 170 |
+
"imatrix": true,
|
| 171 |
+
"protected": false,
|
| 172 |
+
"note": "Small Q2 K-quant.",
|
| 173 |
+
"file": "VELUM-Coder-Q2_K_S.gguf",
|
| 174 |
+
"size_gb": 3.443321615457535,
|
| 175 |
+
"status": "uploaded"
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"name": "IQ2_M",
|
| 179 |
+
"type": "IQ2_M",
|
| 180 |
+
"imatrix": true,
|
| 181 |
+
"protected": false,
|
| 182 |
+
"note": "Higher-quality 2-bit I-Quant.",
|
| 183 |
+
"file": "VELUM-Coder-IQ2_M.gguf",
|
| 184 |
+
"size_gb": 3.3597187101840973,
|
| 185 |
+
"status": "uploaded"
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"name": "IQ2_S",
|
| 189 |
+
"type": "IQ2_S",
|
| 190 |
+
"imatrix": true,
|
| 191 |
+
"protected": false,
|
| 192 |
+
"note": "2-bit I-Quant.",
|
| 193 |
+
"file": "VELUM-Coder-IQ2_S.gguf",
|
| 194 |
+
"size_gb": 3.1925434172153473,
|
| 195 |
+
"status": "uploaded"
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"name": "IQ2_XS",
|
| 199 |
+
"type": "IQ2_XS",
|
| 200 |
+
"imatrix": true,
|
| 201 |
+
"protected": false,
|
| 202 |
+
"note": "Extra-small 2-bit I-Quant.",
|
| 203 |
+
"file": "VELUM-Coder-IQ2_XS.gguf",
|
| 204 |
+
"size_gb": 3.059715658426285,
|
| 205 |
+
"status": "uploaded"
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"name": "IQ2_XXS",
|
| 209 |
+
"type": "IQ2_XXS",
|
| 210 |
+
"imatrix": true,
|
| 211 |
+
"protected": false,
|
| 212 |
+
"note": "Extremely compact 2-bit I-Quant.",
|
| 213 |
+
"file": "VELUM-Coder-IQ2_XXS.gguf",
|
| 214 |
+
"size_gb": 2.888634115457535,
|
| 215 |
+
"status": "uploaded"
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"name": "Q2_0",
|
| 219 |
+
"type": "Q2_0",
|
| 220 |
+
"imatrix": true,
|
| 221 |
+
"protected": false,
|
| 222 |
+
"note": "2.25 bpw Q2_0.",
|
| 223 |
+
"file": "VELUM-Coder-Q2_0.gguf",
|
| 224 |
+
"size_gb": 3.136253744363785,
|
| 225 |
+
"status": "uploaded"
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"name": "TQ2_0",
|
| 229 |
+
"type": "TQ2_0",
|
| 230 |
+
"imatrix": true,
|
| 231 |
+
"protected": false,
|
| 232 |
+
"note": "Experimental ternary ~2-bit build.",
|
| 233 |
+
"file": "VELUM-Coder-TQ2_0.gguf",
|
| 234 |
+
"size_gb": 2.9852375090122223,
|
| 235 |
+
"status": "uploaded"
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"name": "IQ1_M",
|
| 239 |
+
"type": "IQ1_M",
|
| 240 |
+
"imatrix": true,
|
| 241 |
+
"protected": true,
|
| 242 |
+
"note": "Extreme build. IQ1_M body + Q8_0 embedding/output protection.",
|
| 243 |
+
"file": "VELUM-Coder-IQ1_M.gguf",
|
| 244 |
+
"size_gb": 3.7305378019809723,
|
| 245 |
+
"status": "uploaded"
|
| 246 |
+
}
|
| 247 |
+
]
|
| 248 |
+
}
|