GGUF layer package for running Devstral-Small-2-24B-Instruct-2512-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Devstral-Small-2-24B-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/Devstral-Small-2-24B-Instruct-2512-GGUF |
| Model id | unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:UD-Q4_K_XL |
| Family | Devstral |
| Parameter scale | 24B |
| Quantization | UD-Q4_K_XL |
| Layer count | 40 |
| Activation width | 5120 |
| Package size | 13.8 GB |
| Source file | Devstral-Small-2-24B-Instruct-2512-UD-Q4_K_XL.gguf |
| Package repo | meshllm/Devstral-Small-2-24B-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/Devstral-Small-2-24B-Instruct-2512-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Devstral-Small-2-24B-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/Devstral-Small-2-24B-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/Devstral-Small-2-24B-Instruct-2512-GGUF@main/Devstral-Small-2-24B-Instruct-2512-UD-Q4_K_XL.gguf |
| Source revision | main |
| Source SHA-256 | b44e34b78180fc3ab1abbe1edad9f1f3926fdca10eed3bfae168b065e683f6cd |
| Skippy ABI | 0.1.25 |
| Package manifest SHA-256 | 1527887657160605200ea0d37353c695f1fe7d74b8d310b1de2a6e371102b67f |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 1527887657160605200ea0d37353c695f1fe7d74b8d310b1de2a6e371102b67f |
| Metadata | shared/metadata.gguf | 0 tensors, 8.0 MB | 86fec00c5793bcf438dd2d1c5f75f782c79ea84cf6aaa4450bcc2bd146341e68 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 368.0 MB | 5cdea2e2b47b8d751d31151a3f63196b8723fe8588621228b94c126cc9977ea7 |
| Output head | shared/output.gguf | 2 tensors, 533.0 MB | 3c7be3f6156a76320542e283b933580a1988415c2696a3b8b37ad58f5a68be0b |
| 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-2-24B-Instruct-2512-UD-Q4_K_XL.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Devstral-Small-2-24B-Instruct-2512-UD-Q4_K_XL-layers-199/package"
Links
- Source model: unsloth/Devstral-Small-2-24B-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