GGUF layer package for running DeepSeek-R1-Distill-Qwen-14B-Q4_K_M across a local Mesh LLM cluster.
This package is derived from unsloth/DeepSeek-R1-Distill-Qwen-14B-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-Distill-Qwen-14B-GGUF |
| Model id | unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M |
| Family | DeepSeek |
| Parameter scale | 14B |
| Quantization | Q4_K_M |
| Layer count | 48 |
| Activation width | 5120 |
| Package size | 8.6 GB |
| Source file | DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf |
| Package repo | meshllm/DeepSeek-R1-Distill-Qwen-14B-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-Distill-Qwen-14B-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/DeepSeek-R1-Distill-Qwen-14B-Q4_K_M-layers" --split
# Check the mesh and discover the OpenAI-compatible model name.
curl -s http://localhost:3131/api/status
curl -s http://localhost:3131/v1/models
# Send an OpenAI-compatible chat request.
curl -s http://localhost:3131/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF: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-Distill-Qwen-14B-GGUF@main/DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf |
| Source revision | main |
| Source SHA-256 | 67a7933cf2ad596a393c8e13b30bc4da2d50b283e250b78554aed18817eca31c |
| Skippy ABI | 0.1.25 |
| Package manifest SHA-256 | ed42abf28ffba246e1395db3ea7680508ba5bafe0d3458c743474043f52fcaf7 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | ed42abf28ffba246e1395db3ea7680508ba5bafe0d3458c743474043f52fcaf7 |
| Metadata | shared/metadata.gguf | 0 tensors, 5.7 MB | a3d0588bcd39abad3a371f7a0be026cd0d3c85204a0d2d924887a85a3c724104 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 423.3 MB | 75439acb3fb299b37dc2cef8f579ceacc24d2b503b6f6cd2ea77ec829181392e |
| Output head | shared/output.gguf | 2 tensors, 614.8 MB | aafaa3e7bb15175b51254de0a38bc2554f78a85100260d70f26678b5be2126c3 |
| Transformer layers | layers/layer-*.gguf | 48 layer artifacts, 576 tensors, 7.6 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.
skippy-model-package write-package "/source/DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_DeepSeek-R1-Distill-Qwen-14B-Q4_K_M-layers-193/package"
Links
- Source model: unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF
- Mesh LLM website: meshllm.cloud
- Mesh LLM: github.com/Mesh-LLM/mesh-llm
- Discord: discord.gg/rs6fmc63eN
- Package catalog: meshllm/catalog
- Package format: layer-package-repos.md