DeepSeek-R1-Distill-Llama-70B-UD-Q4_K_XL
Distributed GGUF inference package for Mesh LLM
GGUF layer package for running DeepSeek-R1-Distill-Llama-70B-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/DeepSeek-R1-Distill-Llama-70B-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 | UD-Q4_K_XL layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF |
| Model id | unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL |
| Family | DeepSeek |
| Parameter scale | 70B |
| Quantization | UD-Q4_K_XL |
| Layer count | 80 |
| Activation width | 8192 |
| Package size | 40.3 GB |
| Source file | DeepSeek-R1-Distill-Llama-70B-UD-Q4_K_XL.gguf |
| Package repo | meshllm/DeepSeek-R1-Distill-Llama-70B-UD-Q4_K_XL-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-Llama-70B-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/DeepSeek-R1-Distill-Llama-70B-UD-Q4_K_XL-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-Llama-70B-GGUF:UD-Q4_K_XL",
"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-Llama-70B-GGUF@main/DeepSeek-R1-Distill-Llama-70B-UD-Q4_K_XL.gguf |
| Source revision | main |
| Source SHA-256 | 30b01c505f810f02816b9adcd659246cfc0744572fa7ad60feed5bd9ca4e9662 |
| Skippy ABI | 0.1.24 |
| Package manifest SHA-256 | 29727afc930095f84e2ecfdb0b5cd3ed84236728fad37b3a427f4c665d417a7c |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 29727afc930095f84e2ecfdb0b5cd3ed84236728fad37b3a427f4c665d417a7c |
| Metadata | shared/metadata.gguf | 1 tensors, 7.5 MB | e1d5f84bcf4ee2ed6a90cbb1e7b58a5a4a6db2209039b8786147a136c3de6e37 |
| Embeddings | shared/embeddings.gguf | 2 tensors, 571.1 MB | 5ea97740475f22fa617cd934fe09822b9c81fbb6a882a6467b3a5c5ad0785669 |
| Output head | shared/output.gguf | 3 tensors, 829.4 MB | 557d8ae4f584031cf2d198e8877e8dd8bf28ad5e1ed6e7603d34f231967f1916 |
| Transformer layers | layers/layer-*.gguf | 80 layer artifacts, 800 tensors, 39.0 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-Llama-70B-UD-Q4_K_XL.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_DeepSeek-R1-Distill-Llama-70B-UD-Q4_K_XL-layers-193/package"
Links
- Source model: unsloth/DeepSeek-R1-Distill-Llama-70B-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