gguf-quantization

Files (3)

• SKILL.md
• advanced-usage.md · references/
• troubleshooting.md · references/

SKILL.md (first lines)

# GGUF - Quantization Format for llama.cpp

The 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.

## When to use GGUF

**Use GGUF when:**
- Deploying on consumer hardware (laptops, desktops)
- Running on Apple Silicon (M1/M2/M3) with Metal acceleration
- Need CPU inference without GPU requirements
- Want flexible quantization (Q2_K to Q8_0)
- Using local AI tools (LM Studio, Ollama, text-generation-webui)

**Key advantages:**
- **Universal hardware**: CPU, Apple Silicon, NVIDIA, AMD support
- **No Python runtime**: Pure C/C++ inference
- **Flexible quantization**: 2-8 bit with various methods (K-quants)
- **Ecosystem support**: LM Studio, Ollama, koboldcpp, and more
- **imatrix**: Importance matrix for better low-bit quality

**Use alternatives instead:**
- **AWQ/GPTQ**: Maximum accuracy with calibration on NVIDIA GPUs
- **HQQ**: Fast calibration-free quantization for HuggingFace
- **bitsandbytes**: Simple integration with transformers library
- **TensorRT-LLM**: Production NVIDIA deployment with maximum speed

## Quick start

### Installation

```bash
# Clone llama.cpp
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp

# Build (CPU)
make

# Build with CUDA (NVIDIA)
make GGML_CUDA=1

# Build with Metal (Apple Silicon)
make GGML_METAL=1

# Install Python bindings (optional)
uv add llama-cpp-python
```

### Convert model to GGUF

```bash
# Sync dependencies from pyproject.toml
uv sync

# Convert HuggingFace model to GGUF (FP16)
uv run python convert_hf_to_gguf.py ./path/to/model --outfile model-f16.gguf

# Or specify output type
uv run python convert_hf_to_gguf.py ./path/to/model \
    --outfile model-f16.gguf \
    --outtype f16
```

### Quantize model

```bash
# Basic quantization to Q4_K_M
./llama-quantize model-f16.gguf model-q4_k_m.gguf Q4_K_M

# Quantize with importance matrix (better quality)
./llama-imatrix -m model-f16.gguf -f calibration.txt -o model.imatrix
./llama-quantize --imatrix model.imatrix model-f16.gguf model-q4_k_m.gguf Q4_K_M
```

### Run inference

```bash
# CLI inference
./llama-cli -m model-q4_k_m.gguf -p "Hello, how are you?"

# Interactive mode
./llama-cli -m model-q4_k_m.gguf --interactive

# With GPU offload
./llama-cli -m model-q4_k_m.gguf -ngl 35 -p "Hello!"
```

## Quantization types

### K-quant methods (recommended)

| Type | Bits | Size (7B) | Quality | Use Case |
|------|------|-----------|---------|----------|
| Q2_K | 2.5 | ~2.8 GB | Low | Extreme compression |
| Q3_K_S | 3.0 | ~3.0 GB | Low-Med | Memory constrained |
| Q3_K_M | 3.3 | ~3.3 GB | Medium | Balance |
| Q4_K_S | 4.0 | ~3.8 GB | Med-High | Good balance |
| Q4_K_M | 4.5 | ~4.1 GB | High | **Recommended default** |
| Q5_K_S | 5.0 | ~4.6 GB | High | Quality focused |
| Q5_K_M | 5.5 | ~4.8 GB | Very High | High quality |
| Q6_K | 6.0 | ~5.5 GB | Excellent | Near-original |
| Q8_0 | 8.0 | ~7.2 GB | Best | Maximum quality |

### Legacy methods

| Type | Description |
|------|-------------|
| Q4_0 | 4-bit, basic |
| Q4_1 | 4-bit with delta |
| Q5_0 | 5-bit, basic |
| Q5_1 | 5-bit with delta |

**Recommendation**: Use K-quant methods (Q4_K_M, Q5_K_M) for best quality/size ratio.

## Conversion workflows

### Workflow 1: HuggingFace to GGUF

```bash

From nahrun1682/deep-agent-demo, MIT.

More from nahrun1682/deep-agent-demo