Instructions to use meshllm/DeepSeek-R1-Q4_K_M-layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meshllm/DeepSeek-R1-Q4_K_M-layers with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="meshllm/DeepSeek-R1-Q4_K_M-layers",
	filename="layers/layer-000.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use meshllm/DeepSeek-R1-Q4_K_M-layers with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf meshllm/DeepSeek-R1-Q4_K_M-layers
# Run inference directly in the terminal:
llama-cli -hf meshllm/DeepSeek-R1-Q4_K_M-layers

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf meshllm/DeepSeek-R1-Q4_K_M-layers
# Run inference directly in the terminal:
llama-cli -hf meshllm/DeepSeek-R1-Q4_K_M-layers

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 meshllm/DeepSeek-R1-Q4_K_M-layers
# Run inference directly in the terminal:
./llama-cli -hf meshllm/DeepSeek-R1-Q4_K_M-layers

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 meshllm/DeepSeek-R1-Q4_K_M-layers
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meshllm/DeepSeek-R1-Q4_K_M-layers

Use Docker

docker model run hf.co/meshllm/DeepSeek-R1-Q4_K_M-layers

LM Studio
Jan

vLLM

How to use meshllm/DeepSeek-R1-Q4_K_M-layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meshllm/DeepSeek-R1-Q4_K_M-layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meshllm/DeepSeek-R1-Q4_K_M-layers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meshllm/DeepSeek-R1-Q4_K_M-layers

Ollama
How to use meshllm/DeepSeek-R1-Q4_K_M-layers with Ollama:
```
ollama run hf.co/meshllm/DeepSeek-R1-Q4_K_M-layers
```

Unsloth Studio new

How to use meshllm/DeepSeek-R1-Q4_K_M-layers 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 meshllm/DeepSeek-R1-Q4_K_M-layers 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 meshllm/DeepSeek-R1-Q4_K_M-layers to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for meshllm/DeepSeek-R1-Q4_K_M-layers to start chatting

Docker Model Runner
How to use meshllm/DeepSeek-R1-Q4_K_M-layers with Docker Model Runner:
```
docker model run hf.co/meshllm/DeepSeek-R1-Q4_K_M-layers
```

Lemonade

How to use meshllm/DeepSeek-R1-Q4_K_M-layers with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meshllm/DeepSeek-R1-Q4_K_M-layers

Run and chat with the model

lemonade run user.DeepSeek-R1-Q4_K_M-layers-{{QUANT_TAG}}

List all available models

lemonade list

DeepSeek-R1-Q4_K_M-layers / README.md

jamesdumay

Upload README.md with huggingface_hub

1295954 verified 12 days ago

preview code

raw

history blame contribute delete

5.4 kB

	---
	library_name: mesh-llm
	base_model:
	- "unsloth/DeepSeek-R1-GGUF"
	pipeline_tag: text-generation
	tags:
	- gguf
	- mesh-llm
	- layer-package
	- skippy
	- distributed-inference
	- local-inference
	- openai-compatible
	---

	<div align="center">
	<a href="https://www.meshllm.cloud">
	<img src="https://github.com/Mesh-LLM/mesh-llm/raw/main/docs/mesh-llm-logo.svg" alt="Mesh LLM" width="220">
	</a>

	<h1>DeepSeek-R1-Q4_K_M</h1>

	<p>
	<strong>Distributed GGUF inference package for Mesh LLM</strong>
	</p>

	<p>
	<a href="https://www.meshllm.cloud"><img alt="Website" src="https://img.shields.io/badge/Website-meshllm.cloud-111111?style=for-the-badge"></a>
	<a href="https://github.com/Mesh-LLM/mesh-llm"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-Mesh--LLM-24292f?style=for-the-badge&logo=github"></a>
	<a href="https://discord.gg/rs6fmc63eN"><img alt="Discord" src="https://img.shields.io/badge/Discord-Join-5865F2?style=for-the-badge&logo=discord&logoColor=white"></a>
	</p>
	</div>

	GGUF layer package for running DeepSeek-R1-Q4_K_M across a local Mesh LLM cluster.

	This package is derived from [unsloth/DeepSeek-R1-GGUF](https://huggingface.co/unsloth/DeepSeek-R1-GGUF) and keeps the original GGUF distribution split into per-layer artifacts for distributed inference.

	## Highlights

	\| Run locally \| Pool multiple machines \| OpenAI-compatible \| Package variant \|
	\|---\|---\|---\|---\|
	\| Private inference on your hardware \| Split layers across peers \| Serve `/v1/chat/completions` locally \| `Q4_K_M` layer package \|

	## Model Overview

	\| Property \| Value \|
	\|---\|---\|
	\| Source model \| [unsloth/DeepSeek-R1-GGUF](https://huggingface.co/unsloth/DeepSeek-R1-GGUF) \|
	\| Model id \| `unsloth/DeepSeek-R1-GGUF:DeepSeek-R1-Q4_K_M` \|
	\| Family \| DeepSeek \|
	\| Parameter scale \| not recorded \|
	\| Quantization \| `Q4_K_M` \|
	\| Layer count \| 61 \|
	\| Activation width \| 7168 \|
	\| Package size \| 377.0 GB \|
	\| Source file \| `DeepSeek-R1-Q4_K_M/DeepSeek-R1-Q4_K_M-00001-of-00009.gguf` \|
	\| Package repo \| [meshllm/DeepSeek-R1-Q4_K_M-layers](https://huggingface.co/meshllm/DeepSeek-R1-Q4_K_M-layers) \|

	## Recommended Use

	- Local and private inference with Mesh LLM.
	- Multi-machine serving when the full GGUF is too large for one host.
	- OpenAI-compatible chat/completions workflows through Mesh LLM's local API.

	For upstream architecture details, chat template guidance, sampling recommendations, license terms, and benchmark notes, see the source model card: [unsloth/DeepSeek-R1-GGUF](https://huggingface.co/unsloth/DeepSeek-R1-GGUF).

	## Quickstart

	```bash
	# Run this on each machine that should contribute memory/compute.
	mesh-llm serve --model "meshllm/DeepSeek-R1-Q4_K_M-layers" --split
	```

	```bash
	# Check the mesh and discover the OpenAI-compatible model name.
	curl -s http://localhost:3131/api/status
	curl -s http://localhost:3131/v1/models
	```

	```bash
	# Send an OpenAI-compatible chat request.
	curl -s http://localhost:3131/v1/chat/completions \
	-H "Content-Type: application/json" \
	-d '{
	"model": "unsloth/DeepSeek-R1-GGUF:DeepSeek-R1-Q4_K_M",
	"messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
	"max_tokens": 128
	}'
	```

	## Package Variant

	\| Property \| Value \|
	\|---\|---\|
	\| Format \| `layer-package` \|
	\| Canonical source ref \| `unsloth/DeepSeek-R1-GGUF@main/DeepSeek-R1-Q4_K_M/DeepSeek-R1-Q4_K_M-00001-of-00009.gguf` \|
	\| Source revision \| `main` \|
	\| Source SHA-256 \| `d111d9e28b4035e6781906b6451b7866737b4a4ee734baa1575c55d8aa1b4200` \|
	\| Skippy ABI \| `0.1.22` \|
	\| Package manifest SHA-256 \| `f5a62c4f2f5427ac6e083d7666313832cb61a2fc5d8dacfc317b540d8ac82e9d` \|

	## What Is Included

	\| Artifact \| Path \| Contents \| SHA-256 \|
	\|---\|---\|---\|---\|
	\| Manifest \| `model-package.json` \| Package schema, source identity, checksums \| `f5a62c4f2f5427ac6e083d7666313832cb61a2fc5d8dacfc317b540d8ac82e9d` \|
	\| Metadata \| `shared/metadata.gguf` \| 0 tensors, 5.0 MB \| `0e1bf01f20ef69f691126b69c633fd63977cd190bea4182a1c9f41d1537b0ad6` \|
	\| Embeddings \| `shared/embeddings.gguf` \| 1 tensors, 502.1 MB \| `951352774cabdce1e5fe940b30ca85ac8440de68afb6c6eceb451524109991f1` \|
	\| Output head \| `shared/output.gguf` \| 2 tensors, 730.0 MB \| `131fcb580fd1ba667733e39ffc806f819f54928621f40cd47405399a8b9abecb` \|
	\| Transformer layers \| `layers/layer-*.gguf` \| 61 layer artifacts, 1022 tensors, 375.8 GB \| `see model-package.json` \|

	## Validation

	Generated by the Mesh LLM HF Jobs splitter from `mesh-llm` ref `main`.
	Each artifact is checksummed as it is written, uploaded to this repository, and removed from the job workspace before the next artifact is produced.

	```bash
	skippy-model-package write-package "/source/DeepSeek-R1-Q4_K_M/DeepSeek-R1-Q4_K_M-00001-of-00009.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_DeepSeek-R1-Q4_K_M-layers-137/package"
	```

	## Links

	- Source model: [unsloth/DeepSeek-R1-GGUF](https://huggingface.co/unsloth/DeepSeek-R1-GGUF)
	- Mesh LLM website: [meshllm.cloud](https://www.meshllm.cloud)
	- Mesh LLM: [github.com/Mesh-LLM/mesh-llm](https://github.com/Mesh-LLM/mesh-llm)
	- Discord: [discord.gg/rs6fmc63eN](https://discord.gg/rs6fmc63eN)
	- Package catalog: [meshllm/catalog](https://huggingface.co/datasets/meshllm/catalog)
	- Package format: [layer-package-repos.md](https://github.com/Mesh-LLM/mesh-llm/blob/main/docs/specs/layer-package-repos.md)