GGUF layer package for running Mistral-Large-3-675B-Instruct-2512-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Mistral-Large-3-675B-Instruct-2512-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/Mistral-Large-3-675B-Instruct-2512-GGUF |
| Model id | unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:UD-Q4_K_XL |
| Family | Mistral |
| Parameter scale | 675B |
| Quantization | UD-Q4_K_XL |
| Layer count | 61 |
| Activation width | 7168 |
| Package size | 361.7 GB |
| Source file | UD-Q4_K_XL/Mistral-Large-3-675B-Instruct-2512-UD-Q4_K_XL-00001-of-00008.gguf |
| Package repo | meshllm/Mistral-Large-3-675B-Instruct-2512-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/Mistral-Large-3-675B-Instruct-2512-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Mistral-Large-3-675B-Instruct-2512-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/Mistral-Large-3-675B-Instruct-2512-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/Mistral-Large-3-675B-Instruct-2512-GGUF@f1c24a5a3bda6e04ee5439aa8293613fb3179b92/UD-Q4_K_XL/Mistral-Large-3-675B-Instruct-2512-UD-Q4_K_XL-00001-of-00008.gguf |
| Source revision | f1c24a5a3bda6e04ee5439aa8293613fb3179b92 |
| Source SHA-256 | e1bc3401ed9afdeca80301e7cac31951bfae99b70b1e49773af11951ebaca63c |
| Skippy ABI | 0.1.22 |
| Package manifest SHA-256 | ba8f08a4e91aeb9873b051fc03c9bd73186634614955c68a19c7bf615cc7397b |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | ba8f08a4e91aeb9873b051fc03c9bd73186634614955c68a19c7bf615cc7397b |
| Metadata | shared/metadata.gguf | 0 tensors, 8.0 MB | e4529ab9f36b29b49052790d557c0f2457e1b9585296178ac38ad3829552efd2 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 512.0 MB | 71351a7ece52ca01dd0443ac3e9572f72cc092668d3564f629ba1e4b855f7058 |
| Output head | shared/output.gguf | 2 tensors, 743.0 MB | 10c5f843054d9885f082ba1b2d44b389274c3bd39ffd20aa141e9740a0e7ddb1 |
| Transformer layers | layers/layer-*.gguf | 61 layer artifacts, 1025 tensors, 360.5 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/Mistral-Large-3-675B-Instruct-2512-UD-Q4_K_XL-00001-of-00008.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Mistral-Large-3-675B-Instruct-2512-UD-Q4_K_XL-layers-198/package"
Links
- Source model: unsloth/Mistral-Large-3-675B-Instruct-2512-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