[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BHDTS0NZJ1ARR00K9BZ2GD":3,"skill-same:01M7BHDTS0NZJ1ARR00K9BZ2GD":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M7BHDTS0NZJ1ARR00K9BZ2GD","gguf-quantization",null,"GGUF format and llama.cpp quantization for efficient CPU\u002FGPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-gguf\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gguf-quantization\ndescription: GGUF format and llama.cpp quantization for efficient CPU\u002FGPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [GGUF, Quantization, llama.cpp, CPU Inference, Apple Silicon, Model Compression, Optimization]\ndependencies: [llama-cpp-python>=0.2.0]\n---\n\n# GGUF - Quantization Format for llama.cpp\n\nThe GGUF (GPT-Generated Unified Format) is the standard file format for llama.cpp, enabling efficient inference on CPUs, Apple Silicon, and GPUs with flexible quantization options.\n\n## When to use GGUF\n\n**Use GGUF when:**\n- Deploying on consumer hardware (laptops, desktops)\n- Running on Apple Silicon (M1\u002FM2\u002FM3) with Metal acceleration\n- Need CPU inference without GPU requirements\n- Want flexible quantization (Q2_K to Q8_0)\n- Using local AI tools (LM Studio, Ollama, text-generation-webui)\n\n**Key advantages:**\n- **Universal hardware**: CPU, Apple Silicon, NVIDIA, AMD support\n- **No Python runtime**: Pure C\u002FC++ inference\n- **Flexible quantization**: 2-8 bit with various methods (K-quants)\n- **Ecosystem support**: LM Studio, Ollama, koboldcpp, and more\n- **imatrix**: Importance matrix for better low-bit quality\n\n**Use alternatives instead:**\n- **AWQ\u002FGPTQ**: Maximum accuracy with calibration on NVIDIA GPUs\n- **HQQ**: Fast calibration-free quantization for HuggingFace\n- **bitsandbytes**: Simple integration with transformers library\n- **TensorRT-LLM**: Production NVIDIA deployment with maximum speed\n\n## Quick start\n\n### Installation\n\n```bash\n# Clone llama.cpp\ngit clone https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp\ncd llama.cpp\n\n# Build (CPU)\nmake\n\n# Build with CUDA (NVIDIA)\nmake GGML_CUDA=1\n\n# Build with Metal (Apple Silicon)\nmake GGML_METAL=1\n\n# Install Python bindings (optional)\npip install llama-cpp-python\n```\n\n### Convert model to GGUF\n\n```bash\n# Install requirements\npip install -r requirements.txt\n\n# Convert HuggingFace model to GGUF (FP16)\npython convert_hf_to_gguf.py .\u002Fpath\u002Fto\u002Fmodel --outfile model-f16.gguf\n\n# Or specify output type\npython convert_hf_to_gguf.py .\u002Fpath\u002Fto\u002Fmodel \\\n    --outfile model-f16.gguf \\\n    --outtype f16\n```\n\n### Quantize model\n\n```bash\n# Basic quantization to Q4_K_M\n.\u002Fllama-quantize model-f16.gguf model-q4_k_m.gguf Q4_K_M\n\n# Quantize with importance matrix (better quality)\n.\u002Fllama-imatrix -m model-f16.gguf -f calibration.txt -o model.imatrix\n.\u002Fllama-quantize --imatrix model.imatrix model-f16.gguf model-q4_k_m.gguf Q4_K_M\n```\n\n### Run inference\n\n```bash\n# CLI inference\n.\u002Fllama-cli -m model-q4_k_m.gguf -p \"Hello, how are you?\"\n\n# Interactive mode\n.\u002Fllama-cli -m model-q4_k_m.gguf --interactive\n\n# With GPU offload\n.\u002Fllama-cli -m model-q4_k_m.gguf -ngl 35 -p \"Hello!\"\n```\n\n## Quantization types\n\n### K-quant methods (recommended)\n\n| Type | Bits | Size (7B) | Quality | Use Case |\n|------|------|-----------|---------|----------|\n| Q2_K | 2.5 | ~2.8 GB | Low | Extreme compression |\n| Q3_K_S | 3.0 | ~3.0 GB | Low-Med | Memory constrained |\n| Q3_K_M | 3.3 | ~3.3 GB | Medium | Balance |\n| Q4_K_S | 4.0 | ~3.8 GB | Med-High | Good balance |\n| Q4_K_M | 4.5 | ~4.1 GB | High | **Recommended default** |\n| Q5_K_S | 5.0 | ~4.6 GB | High | Quality focused |\n| Q5_K_M | 5.5 | ~4.8 GB | Very High | High quality |\n| Q6_K | 6.0 | ~5.5 GB | Excellent | Near-original |\n| Q8_0 | 8.0 | ~7.2 GB | Best | Maximum quality |\n\n### Legacy methods\n\n| Type | Description |\n|------|-------------|\n| Q4_0 | 4-bit, basic |\n| Q4_1 | 4-bit with delta |\n| Q5_0 | 5-bit, basic |\n| Q5_1 | 5-bit with delta |\n\n**Recommendation**: Use K-quant methods (Q4_K_M, Q5_K_M) for best quality\u002Fsize ratio.\n\n## Conversion workflows\n\n### Workflow 1: HuggingFace to GGUF\n\n```bash\n# 1. Download model\nhuggingface-cli download meta-llama\u002FLlama-3.1-8B --local-dir .\u002Fllama-3.1-8b\n\n# 2. Convert to GGUF (FP16)\npython convert_hf_to_gguf.py .\u002Fllama-3.1-8b \\\n    --outfile llama-3.1-8b-f16.gguf \\\n    --outtype f16\n\n# 3. Quantize\n.\u002Fllama-quantize llama-3.1-8b-f16.gguf llama-3.1-8b-q4_k_m.gguf Q4_K_M\n\n# 4. Test\n.\u002Fllama-cli -m llama-3.1-8b-q4_k_m.gguf -p \"Hello!\" -n 50\n```\n\n### Workflow 2: With importance matrix (better quality)\n\n```bash\n# 1. Convert to GGUF\npython convert_hf_to_gguf.py .\u002Fmodel --outfile model-f16.gguf\n\n# 2. Create calibration text (diverse samples)\ncat > calibration.txt \u003C\u003C 'EOF'\nThe quick brown fox jumps over the lazy dog.\nMachine learning is a subset of artificial intelligence.\nPython is a popular programming language.\n# Add more diverse text samples...\nEOF\n\n# 3. Generate importance matrix\n.\u002Fllama-imatrix -m model-f16.gguf \\\n    -f calibration.txt \\\n    --chunk 512 \\\n    -o model.imatrix \\\n    -ngl 35  # GPU layers if available\n\n# 4. Quantize with imatrix\n.\u002Fllama-quantize --imatrix model.imatrix \\\n    model-f16.gguf \\\n    model-q4_k_m.gguf \\\n    Q4_K_M\n```\n\n### Workflow 3: Multiple quantizations\n\n```bash\n#!\u002Fbin\u002Fbash\nMODEL=\"llama-3.1-8b-f16.gguf\"\nIMATRIX=\"llama-3.1-8b.imatrix\"\n\n# Generate imatrix once\n.\u002Fllama-imatrix -m $MODEL -f wiki.txt -o $IMATRIX -ngl 35\n\n# Create multiple quantizations\nfor QUANT in Q4_K_M Q5_K_M Q6_K Q8_0; do\n    OUTPUT=\"llama-3.1-8b-${QUANT,,}.gguf\"\n    .\u002Fllama-quantize --imatrix $IMATRIX $MODEL $OUTPUT $QUANT\n    echo \"Created: $OUTPUT ($(du -h $OUTPUT | cut -f1))\"\ndone\n```\n\n## Python usage\n\n### llama-cpp-python\n\n```python\nfrom llama_cpp import Llama\n\n# Load model\nllm = Llama(\n    model_path=\".\u002Fmodel-q4_k_m.gguf\",\n    n_ctx=4096,          # Context window\n    n_gpu_layers=35,     # GPU offload (0 for CPU only)\n    n_threads=8          # CPU threads\n)\n\n# Generate\noutput = llm(\n    \"What is machine learning?\",\n    max_tokens=256,\n    temperature=0.7,\n    stop=[\"\u003C\u002Fs>\", \"\\n\\n\"]\n)\nprint(output[\"choices\"][0][\"text\"])\n```\n\n### Chat completion\n\n```python\nfrom llama_cpp import Llama\n\nllm = Llama(\n    model_path=\".\u002Fmodel-q4_k_m.gguf\",\n    n_ctx=4096,\n    n_gpu_layers=35,\n    chat_format=\"llama-3\"  # Or \"chatml\", \"mistral\", etc.\n)\n\nmessages = [\n    {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n    {\"role\": \"user\", \"content\": \"What is Python?\"}\n]\n\nresponse = llm.create_chat_completion(\n    messages=messages,\n    max_tokens=256,\n    temperature=0.7\n)\nprint(response[\"choices\"][0][\"message\"][\"content\"])\n```\n\n### Streaming\n\n```python\nfrom llama_cpp import Llama\n\nllm = Llama(model_path=\".\u002Fmodel-q4_k_m.gguf\", n_gpu_layers=35)\n\n# Stream tokens\nfor chunk in llm(\n    \"Explain quantum computing:\",\n    max_tokens=256,\n    stream=True\n):\n    print(chunk[\"choices\"][0][\"text\"], end=\"\", flush=True)\n```\n\n## Server mode\n\n### Start OpenAI-compatible server\n\n```bash\n# Start server\n.\u002Fllama-server -m model-q4_k_m.gguf \\\n    --host 0.0.0.0 \\\n    --port 8080 \\\n    -ngl 35 \\\n    -c 4096\n\n# Or with Python bindings\npython -m llama_cpp.server \\\n    --model model-q4_k_m.gguf \\\n    --n_gpu_layers 35 \\\n    --host 0.0.0.0 \\\n    --port 8080\n```\n\n### Use with OpenAI client\n\n```python\nfrom openai import OpenAI\n\nclient = OpenAI(\n    base_url=\"http:\u002F\u002Flocalhost:8080\u002Fv1\",\n    api_key=\"not-needed\"\n)\n\nresponse = client.chat.completions.create(\n    model=\"local-model\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello!\"}],\n    max_tokens=256\n)\nprint(response.choices[0].message.content)\n```\n\n## Hardware optimization\n\n### Apple Silicon (Metal)\n\n```bash\n# Build with Metal\nmake clean && make GGML_METAL=1\n\n# Run with Metal acceleration\n.\u002Fllama-cli -m model.gguf -ngl 99 -p \"Hello\"\n\n# Python with Metal\nllm = Llama(\n    model_path=\"model.gguf\",\n    n_gpu_layers=99,     # Offload all layers\n    n_threads=1          # Metal handles parallelism\n)\n```\n\n### NVIDIA CUDA\n\n```bash\n# Build with CUDA\nmake clean && make GGML_CUDA=1\n\n# Run with CUDA\n.\u002Fllama-cli -m model.gguf -ngl 35 -p \"Hello\"\n\n# Specify GPU\nCUDA_VISIBLE_DEVICES=0 .\u002Fllama-cli -m model.gguf -ngl 35\n```\n\n### CPU optimization\n\n```bash\n# Build with AVX2\u002FAVX512\nmake clean && make\n\n# Run with optimal threads\n.\u002Fllama-cli -m model.gguf -t 8 -p \"Hello\"\n\n# Python CPU config\nllm = Llama(\n    model_path=\"model.gguf\",\n    n_gpu_layers=0,      # CPU only\n    n_threads=8,         # Match physical cores\n    n_batch=512          # Batch size for prompt processing\n)\n```\n\n## Integration with tools\n\n### Ollama\n\n```bash\n# Create Modelfile\ncat > Modelfile \u003C\u003C 'EOF'\nFROM .\u002Fmodel-q4_k_m.gguf\nTEMPLATE \"\"\"{{ .System }}\n{{ .Prompt }}\"\"\"\nPARAMETER temperature 0.7\nPARAMETER num_ctx 4096\nEOF\n\n# Create Ollama model\nollama create mymodel -f Modelfile\n\n# Run\nollama run mymodel \"Hello!\"\n```\n\n### LM Studio\n\n1. Place GGUF file in `~\u002F.cache\u002Flm-studio\u002Fmodels\u002F`\n2. Open LM Studio and select the model\n3. Configure context length and GPU offload\n4. Start inference\n\n### text-generation-webui\n\n```bash\n# Place in models folder\ncp model-q4_k_m.gguf text-generation-webui\u002Fmodels\u002F\n\n# Start with llama.cpp loader\npython server.py --model model-q4_k_m.gguf --loader llama.cpp --n-gpu-layers 35\n```\n\n## Best practices\n\n1. **Use K-quants**: Q4_K_M offers best quality\u002Fsize balance\n2. **Use imatrix**: Always use importance matrix for Q4 and below\n3. **GPU offload**: Offload as many layers as VRAM allows\n4. **Context length**: Start with 4096, increase if needed\n5. **Thread count**: Match physical CPU cores, not logical\n6. **Batch size**: Increase n_batch for faster prompt processing\n\n## Common issues\n\n**Model loads slowly:**\n```bash\n# Use mmap for faster loading\n.\u002Fllama-cli -m model.gguf --mmap\n```\n\n**Out of memory:**\n```bash\n# Reduce GPU layers\n.\u002Fllama-cli -m model.gguf -ngl 20  # Reduce from 35\n\n# Or use smaller quantization\n.\u002Fllama-quantize model-f16.gguf model-q3_k_m.gguf Q3_K_M\n```\n\n**Poor quality at low bits:**\n```bash\n# Always use imatrix for Q4 and below\n.\u002Fllama-imatrix -m model-f16.gguf -f calibration.txt -o model.imatrix\n.\u002Fllama-quantize --imatrix model.imatrix model-f16.gguf model-q4_k_m.gguf Q4_K_M\n```\n\n## References\n\n- **[Advanced Usage](references\u002Fadvanced-usage.md)** - Batching, speculative decoding, custom builds\n- **[Troubleshooting](references\u002Ftroubleshooting.md)** - Common issues, debugging, benchmarks\n\n## Resources\n\n- **Repository**: https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp\n- **Python Bindings**: https:\u002F\u002Fgithub.com\u002Fabetlen\u002Fllama-cpp-python\n- **Pre-quantized Models**: https:\u002F\u002Fhuggingface.co\u002FTheBloke\n- **GGUF Converter**: https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fggml-org\u002Fgguf-my-repo\n- **License**: MIT\n","# GGUF - Quantization Format for llama.cpp\n\nThe GGUF (GPT-Generated Unified Format) is the standard file format for llama.cpp, enabling efficient inference on CPUs, Apple Silicon, and GPUs with flexible quantization options.\n\n## When to use GGUF\n\n**Use GGUF when:**\n- Deploying on consumer hardware (laptops, desktops)\n- Running on Apple Silicon (M1\u002FM2\u002FM3) with Metal acceleration\n- Need CPU inference without GPU requirements\n- Want flexible quantization (Q2_K to Q8_0)\n- Using local AI tools (LM Studio, Ollama, text-generation-webui)\n\n**Key advantages:**\n- **Universal hardware**: CPU, Apple Silicon, NVIDIA, AMD support\n- **No Python runtime**: Pure C\u002FC++ inference\n- **Flexible quantization**: 2-8 bit with various methods (K-quants)\n- **Ecosystem support**: LM Studio, Ollama, koboldcpp, and more\n- **imatrix**: Importance matrix for better low-bit quality\n\n**Use alternatives instead:**\n- **AWQ\u002FGPTQ**: Maximum accuracy with calibration on NVIDIA GPUs\n- **HQQ**: Fast calibration-free quantization for HuggingFace\n- **bitsandbytes**: Simple integration with transformers library\n- **TensorRT-LLM**: Production NVIDIA deployment with maximum speed\n\n## Quick start\n\n### Installation\n\n```bash\n# Clone llama.cpp\ngit clone https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp\ncd llama.cpp\n\n# Build (CPU)\nmake\n\n# Build with CUDA (NVIDIA)\nmake GGML_CUDA=1\n\n# Build with Metal (Apple Silicon)\nmake GGML_METAL=1\n\n# Install Python bindings (optional)\npip install llama-cpp-python\n```\n\n### Convert model to GGUF\n\n```bash\n# Install requirements\npip install -r requirements.txt\n\n# Convert HuggingFace model to GGUF (FP16)\npython convert_hf_to_gguf.py .\u002Fpath\u002Fto\u002Fmodel --outfile model-f16.gguf\n\n# Or specify output type\npython convert_hf_to_gguf.py .\u002Fpath\u002Fto\u002Fmodel \\\n    --outfile model-f16.gguf \\\n    --outtype f16\n```\n\n### Quantize model\n\n```bash\n# Basic quantization to Q4_K_M\n.\u002Fllama-quantize model-f16.gguf model-q4_k_m.gguf Q4_K_M\n\n# Quantize with importance matrix (better quality)\n.\u002Fllama-imatrix -m model-f16.gguf -f calibration.txt -o model.imatrix\n.\u002Fllama-quantize --imatrix model.imatrix model-f16.gguf model-q4_k_m.gguf Q4_K_M\n```\n\n### Run inference\n\n```bash\n# CLI inference\n.\u002Fllama-cli -m model-q4_k_m.gguf -p \"Hello, how are you?\"\n\n# Interactive mode\n.\u002Fllama-cli -m model-q4_k_m.gguf --interactive\n\n# With GPU offload\n.\u002Fllama-cli -m model-q4_k_m.gguf -ngl 35 -p \"Hello!\"\n```\n\n## Quantization types\n\n### K-quant methods (recommended)\n\n| Type | Bits | Size (7B) | Quality | Use Case |\n|------|------|-----------|---------|----------|\n| Q2_K | 2.5 | ~2.8 GB | Low | Extreme compression |\n| Q3_K_S | 3.0 | ~3.0 GB | Low-Med | Memory constrained |\n| Q3_K_M | 3.3 | ~3.3 GB | Medium | Balance |\n| Q4_K_S | 4.0 | ~3.8 GB | Med-High | Good balance |\n| Q4_K_M | 4.5 | ~4.1 GB | High | **Recommended default** |\n| Q5_K_S | 5.0 | ~4.6 GB | High | Quality focused |\n| Q5_K_M | 5.5 | ~4.8 GB | Very High | High quality |\n| Q6_K | 6.0 | ~5.5 GB | Excellent | Near-original |\n| Q8_0 | 8.0 | ~7.2 GB | Best | Maximum quality |\n\n### Legacy methods\n\n| Type | Description |\n|------|-------------|\n| Q4_0 | 4-bit, basic |\n| Q4_1 | 4-bit with delta |\n| Q5_0 | 5-bit, basic |\n| Q5_1 | 5-bit with delta |\n\n**Recommendation**: Use K-quant methods (Q4_K_M, Q5_K_M) for best quality\u002Fsize ratio.\n\n## Conversion workflows\n\n### Workflow 1: HuggingFace to GGUF\n\n```bash\n# 1. Download model\nhuggingface-cli download meta-llama\u002FLlama-3.1-8B --local-dir .\u002Fllama-3.1-8b\n\n# 2. Convert to GGUF (FP16)\npython convert_hf_to_gguf.py .\u002Fllama-3.1-8b \\\n    --outfile llama-3.1-8b-f16.gguf \\\n    --outtype f16\n\n# 3. Quantize\n.\u002Fllama-quantize llama-3.1-8b-f16.gguf llama-3.1-8b-q4_k_m.gguf Q4_K_M\n\n# 4. Test\n.\u002Fllama-cli -m llama-3.1-8b-q4_k_m.gguf -p \"Hello!\" -n 50\n```\n\n### Workflow 2: With importance matrix (better quality)\n\n```bash\n# 1. Convert to GGUF\npython convert_hf_to_gguf.py .\u002Fmodel --outfile model-f16.gguf\n\n# 2. Create calibration text (diverse samples)\ncat > calibration.txt \u003C\u003C 'EOF'\nThe quick brown fox jumps over the lazy dog.\nMachine learning is a subset of artificial intelligence.\nPython is a popular programming language.\n# Add more diverse text samples...\nEOF\n\n# 3. Generate importance matrix\n.\u002Fllama-imatrix -m model-f16.gguf \\\n    -f calibration.txt \\\n    --chunk 512 \\\n    -o model.imatrix \\\n    -ngl 35  # GPU layers if available\n\n# 4. Quantize with imatrix\n.\u002Fllama-quantize --imatrix model.imatrix \\\n    model-f16.gguf \\\n    model-q4_k_m.gguf \\\n    Q4_K_M\n```\n\n### Workflow 3: Multiple quantizations\n\n```bash\n#!\u002Fbin\u002Fbash\nMODEL=\"llama-3.1-8b-f16.gguf\"\nIMATRIX=\"llama-3.1-8b.imatrix\"\n\n# Generate imatrix once\n.\u002Fllama-imatrix -m $MODEL -f wiki.txt -o $IMATRIX -ngl 35\n\n# Create multiple quantizations\nfor QUANT in Q4_K_M Q5_K_M Q6_K Q8_0; do\n    OUTPUT=\"llama-3.1-8b-${QUANT,,}.gguf\"\n    .\u002Fllama-quantize --imatrix $IMATRIX $MODEL $OUTPUT $QUANT\n    echo \"Created: $OUTPUT ($(du -h $OUTPUT | cut -f1))\"\ndone\n```\n\n## Python usage\n\n### llama-cpp-python\n\n```python\nfrom llama_cpp import Llama\n\n# Load model\nllm = Llama(\n    model_path=\".\u002Fmodel-q4_k_m.gguf\",\n    n_ctx=4096,          # Context window\n    n_gpu_layers=35,     # GPU offload (0 for CPU only)\n    n_threads=8          # CPU threads\n)\n\n# Generate\noutput = llm(\n    \"What is machine learning?\",\n    max_tokens=256,\n    temperature=0.7,\n    stop=[\"\u003C\u002Fs>\", \"\\n\\n\"]\n)\nprint(output[\"choices\"][0][\"text\"])\n```\n\n### Chat completion\n\n```python\nfrom llama_cpp import Llama\n\nllm = Llama(\n    model_path=\".\u002Fmodel-q4_k_m.gguf\",\n    n_ctx=4096,\n    n_gpu_layers=35,\n    chat_format=\"llama-3\"  # Or \"chatml\", \"mistral\", etc.\n)\n\nmessages = [\n    {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n    {\"role\": \"user\", \"content\": \"What is Python?\"}\n]\n\nresponse = llm.create_chat_completion(\n    messages=messages,\n    max_tokens=256,\n    temperature=0.7\n)\nprint(response[\"choices\"][0][\"message\"][\"content\"])\n```\n\n### Streaming\n\n```python\nfrom llama_cpp import Llama\n\nllm = Llama(model_path=\".\u002Fmodel-q4_k_m.gguf\", n_gpu_layers=35)\n\n# Stream tokens\nfor chunk in llm(\n    \"Explain quantum computing:\",\n    max_tokens=256,\n    stream=True\n):\n    print(chunk[\"choices\"][0][\"text\"], end=\"\", flush=True)\n```\n\n## Server mode\n\n### Start OpenAI-compatible server\n\n```bash\n# Start server\n.\u002Fllama-server -m model-q4_k_m.gguf \\\n    --host 0.0.0.0 \\\n    --port 8080 \\\n    -ngl 35 \\\n    -c 4096\n\n# Or with Python bindings\npython -m llama_cpp.server \\\n    --model model-q4_k_m.gguf \\\n    --n_gpu_layers 35 \\\n    --host 0.0.0.0 \\\n    --port 8080\n```\n\n### Use with OpenAI client\n\n```python\nfrom openai import OpenAI\n\nclient = OpenAI(\n    base_url=\"http:\u002F\u002Flocalhost:8080\u002Fv1\",\n    api_key=\"not-needed\"\n)\n\nresponse = client.chat.completions.create(\n    model=\"local-model\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello!\"}],\n    max_tokens=256\n)\nprint(response.choices[0].message.content)\n```\n\n## Hardware optimization\n\n### Apple Silicon (Metal)\n\n```bash\n# Build with Metal\nmake clean && make GGML_METAL=1\n\n# Run with Metal acceleration\n.\u002Fllama-cli -m model.gguf -ngl 99 -p \"Hello\"\n\n# Python with Metal\nllm = Llama(\n    model_path=\"model.gguf\",\n    n_gpu_layers=99,     # Offload all layers\n    n_threads=1          # Metal handles parallelism\n)\n```\n\n### NVIDIA CUDA\n\n```bash\n# Build with CUDA\nmake clean && make GGML_CUDA=1\n\n# Run with CUDA\n.\u002Fllama-cli -m model.gguf -ngl 35 -p \"Hello\"\n\n# Specify GPU\nCUDA_VISIBLE_DEVICES=0 .\u002Fllama-cli -m model.gguf -ngl 35\n```\n\n### CPU optimization\n\n```bash\n# Build with AVX2\u002FAVX512\nmake clean && make\n\n# Run with optimal threads\n.\u002Fllama-cli -m model.gguf -t 8 -p \"Hello\"\n\n# Python CPU config\nllm = Llama(\n    model_path=\"model.gguf\",\n    n_gpu_layers=0,      # CPU only\n    n_threads=8,         # Match physical cores\n    n_batch=512          # Batch size for prompt processing\n)\n```\n\n## Integration with tools\n\n### Ollama\n\n```bash\n# Create Modelfile\ncat > Modelfile \u003C\u003C 'EOF'\nFROM .\u002Fmodel-q4_k_m.gguf\nTEMPLATE \"\"\"{{ .System }}\n{{ .Prompt }}\"\"\"\nPARAMETER temperature 0.7\nPARAMETER num_ctx 4096\nEOF\n\n# Create Ollama model\nollama create mymodel -f Modelfile\n\n# Run\nollama run mymodel \"Hello!\"\n```\n\n### LM Studio\n\n1. Place GGUF file in `~\u002F.cache\u002Flm-studio\u002Fmodels\u002F`\n2. Open LM Studio and select the model\n3. Configure context length and GPU offload\n4. Start inference\n\n### text-generation-webui\n\n```bash\n# Place in models folder\ncp model-q4_k_m.gguf text-generation-webui\u002Fmodels\u002F\n\n# Start with llama.cpp loader\npython server.py --model model-q4_k_m.gguf --loader llama.cpp --n-gpu-layers 35\n```\n\n## Best practices\n\n1. **Use K-quants**: Q4_K_M offers best quality\u002Fsize balance\n2. **Use imatrix**: Always use importance matrix for Q4 and below\n3. **GPU offload**: Offload as many layers as VRAM allows\n4. **Context length**: Start with 4096, increase if needed\n5. **Thread count**: Match physical CPU cores, not logical\n6. **Batch size**: Increase n_batch for faster prompt processing\n\n## Common issues\n\n**Model loads slowly:**\n```bash\n# Use mmap for faster loading\n.\u002Fllama-cli -m model.gguf --mmap\n```\n\n**Out of memory:**\n```bash\n# Reduce GPU layers\n.\u002Fllama-cli -m model.gguf -ngl 20  # Reduce from 35\n\n# Or use smaller quantization\n.\u002Fllama-quantize model-f16.gguf model-q3_k_m.gguf Q3_K_M\n```\n\n**Poor quality at low bits:**\n```bash\n# Always use imatrix for Q4 and below\n.\u002Fllama-imatrix -m model-f16.gguf -f calibration.txt -o model.imatrix\n.\u002Fllama-quantize --imatrix model.imatrix model-f16.gguf model-q4_k_m.gguf Q4_K_M\n```\n\n## References\n\n- **[Advanced Usage](references\u002Fadvanced-usage.md)** - Batching, speculative decoding, custom builds\n- **[Troubleshooting](references\u002Ftroubleshooting.md)** - Common issues, debugging, benchmarks\n\n## Resources\n\n- **Repository**: https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp\n- **Python Bindings**: https:\u002F\u002Fgithub.com\u002Fabetlen\u002Fllama-cpp-python\n- **Pre-quantized Models**: https:\u002F\u002Fhuggingface.co\u002FTheBloke\n- **GGUF Converter**: https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fggml-org\u002Fgguf-my-repo\n- **License**: MIT\n",{"name":5,"tags":24,"author":32,"license":15,"version":33,"description":7,"dependencies":34},[25,26,27,28,29,30,31],"GGUF","Quantization","llama.cpp","CPU Inference","Apple Silicon","Model Compression","Optimization","Orchestra Research","1.0.0",[35],"llama-cpp-python>=0.2.0","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-gguf",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill gguf-quantization",{"tool":51,"command":52},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill gguf-quantization",{"tool":54,"command":55},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill gguf-quantization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-gguf\u002FSKILL.md",true,[59,65],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fadvanced-usage.md","REFERENCE","参考文档",10887,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-gguf\u002Freferences\u002Fadvanced-usage.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",8904,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-gguf\u002Freferences\u002Ftroubleshooting.md",[70,77,84,91,98,105],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]