GGUF layer package for running Devstral-Small-2505-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Devstral-Small-2505-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/Devstral-Small-2505-GGUF |
| Model id | unsloth/Devstral-Small-2505-GGUF:UD-Q4_K_XL |
| Family | Devstral |
| Parameter scale | not recorded |
| Quantization | UD-Q4_K_XL |
| Layer count | 40 |
| Activation width | 5120 |
| Package size | 13.9 GB |
| Source file | Devstral-Small-2505-UD-Q4_K_XL.gguf |
| Package repo | meshllm/Devstral-Small-2505-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/Devstral-Small-2505-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Devstral-Small-2505-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/Devstral-Small-2505-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/Devstral-Small-2505-GGUF@main/Devstral-Small-2505-UD-Q4_K_XL.gguf |
| Source revision | main |
| Source SHA-256 | d8d48447e4de4c6ffab551d77c48d0898b50ea5d2b7f71ebf48332a7cb58c9a6 |
| Skippy ABI | 0.1.24 |
| Package manifest SHA-256 | e87484ca8d6e68928149bf66db39629fbdce516336e64a58d3787c71bc571ed0 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | e87484ca8d6e68928149bf66db39629fbdce516336e64a58d3787c71bc571ed0 |
| Metadata | shared/metadata.gguf | 0 tensors, 7.5 MB | 7e1e6b928ef6c36452ab4bbe266b4f145ec1ac735b859c7bdf4bff282a150411 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 367.5 MB | c8bfa621b11ae8d27370f6e96010669084f5cb1ae85ba454ce8b7dfede2a833a |
| Output head | shared/output.gguf | 2 tensors, 532.5 MB | e653228ee2dc92d6f06af9aaffba9974730c89dadb22dd32482324c90e947614 |
| Transformer layers | layers/layer-*.gguf | 40 layer artifacts, 360 tensors, 13.0 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/Devstral-Small-2505-UD-Q4_K_XL.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Devstral-Small-2505-UD-Q4_K_XL-layers-193/package"
Links
- Source model: unsloth/Devstral-Small-2505-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