GGUF layer package for running DeepSeek-V3.1-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/DeepSeek-V3.1-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-V3.1-GGUF |
| Model id | unsloth/DeepSeek-V3.1-GGUF:UD-Q4_K_XL |
| Family | DeepSeek |
| Parameter scale | not recorded |
| Quantization | UD-Q4_K_XL |
| Layer count | 61 |
| Activation width | 7168 |
| Package size | 360.6 GB |
| Source file | UD-Q4_K_XL/DeepSeek-V3.1-UD-Q4_K_XL-00001-of-00008.gguf |
| Package repo | meshllm/DeepSeek-V3.1-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-V3.1-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/DeepSeek-V3.1-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-V3.1-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-V3.1-GGUF@main/UD-Q4_K_XL/DeepSeek-V3.1-UD-Q4_K_XL-00001-of-00008.gguf |
| Source revision | main |
| Source SHA-256 | b8800cbc7a53fe085806de8c2856b22fe845f8e1e1ebbdb25a6a5f48fa4d043c |
| Skippy ABI | 0.1.25 |
| Package manifest SHA-256 | 7060d4d8714c84bef2c0f3380fea6b5614d95f9c112b1f1e63fc453bae7d796d |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 7060d4d8714c84bef2c0f3380fea6b5614d95f9c112b1f1e63fc453bae7d796d |
| Metadata | shared/metadata.gguf | 0 tensors, 5.0 MB | 9ce60d15a7e6b2705511236843f2c1e0251ffae69740c49672bf7854f3a9e63f |
| Embeddings | shared/embeddings.gguf | 1 tensors, 502.1 MB | 37e1d784bbbe12e9bbf5f9ed80103f325377bd0ab2b0085007084e481fb7063a |
| Output head | shared/output.gguf | 2 tensors, 730.0 MB | 707a0ec74e25a1f29c2d921ff543a029638475ef7e5165dc7c26416ca24fcbb7 |
| Transformer layers | layers/layer-*.gguf | 61 layer artifacts, 1083 tensors, 359.4 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/UD-Q4_K_XL/DeepSeek-V3.1-UD-Q4_K_XL-00001-of-00008.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_DeepSeek-V3.1-UD-Q4_K_XL-layers-193/package"
Links
- Source model: unsloth/DeepSeek-V3.1-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