How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF:# Run inference directly in the terminal:
llama cli -hf mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF: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 mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF:# Run inference directly in the terminal:
./llama-cli -hf mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF: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 mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF:Use Docker
docker model run hf.co/mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF:Quick Links
DeepSeek-Coder-V2-Lite-Instruct-GGUF
GGUF quantizations of DeepSeek-Coder-V2-Lite-Instruct with imatrix calibration for improved accuracy at lower bit depths.
Available Quants
| Quant | Size | Use Case |
|---|---|---|
| Q6_K | ~13GB | Best quality, high VRAM |
| Q5_K_M | ~11GB | Recommended balance |
| Q4_K_M | ~9GB | Low VRAM / fast inference |
All quants use imatrix calibration data for better perplexity vs. standard quants.
Usage
Load with llama.cpp, Ollama, LM Studio, or any GGUF-compatible runtime.
Original Model
- Downloads last month
- 124
Hardware compatibility
Log In to add your hardware
4-bit
5-bit
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF
Base model
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF:# Run inference directly in the terminal: llama cli -hf mad-lab-ai/deepseek-coder-v2-lite-instruct-GGUF: