Instructions to use eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use eaddario/DeepSeek-R1-Distill-Llama-8B-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 eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF: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 eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF: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 eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eaddario/DeepSeek-R1-Distill-Llama-8B-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": "eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M

Ollama
How to use eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF with Ollama:
```
ollama run hf.co/eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M
```

Lemonade

How to use eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Llama-8B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

DeepSeek-R1-Distill-Llama-8B-GGUF / scores /DeepSeek-R1-Distill-Llama-8B-iq3_m.tqa

eaddario

Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores

6fcfa91 verified over 1 year ago

Raw

History Blame

824 Bytes

	build: 5080 (78a1ba0a) with Apple clang version 16.0.0 (clang-1600.0.26.6) for arm64-apple-darwin24.2.0
	llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
	llama_model_loader: loaded meta data with 33 key-value pairs and 292 tensors from ./DeepSeek-R1-Distill-Llama-8B-IQ3_M.gguf (version GGUF V3 (latest))

	Final result: 30.4000 +/- 1.6807
	Random chance: 19.8992 +/- 1.4588


	llama_perf_context_print: load time = 288.85 ms
	llama_perf_context_print: prompt eval time = 162182.30 ms / 50072 tokens ( 3.24 ms per token, 308.74 tokens per second)
	llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
	llama_perf_context_print: total time = 164031.50 ms / 50073 tokens
	ggml_metal_free: deallocating