GGUF layer package for running MiMo-V2.5-Pro-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/MiMo-V2.5-Pro-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/MiMo-V2.5-Pro-GGUF |
| Model id | unsloth/MiMo-V2.5-Pro-GGUF:UD-Q4_K_XL |
| Family | MiMo |
| Parameter scale | not recorded |
| Quantization | UD-Q4_K_XL |
| Layer count | 73 |
| Activation width | 6144 |
| Package size | 588.1 GB |
| Source file | UD-Q4_K_XL/MiMo-V2.5-Pro-UD-Q4_K_XL-00001-of-00015.gguf |
| Package repo | meshllm/MiMo-V2.5-Pro-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/MiMo-V2.5-Pro-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/MiMo-V2.5-Pro-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/MiMo-V2.5-Pro-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/MiMo-V2.5-Pro-GGUF@main/UD-Q4_K_XL/MiMo-V2.5-Pro-UD-Q4_K_XL-00001-of-00015.gguf |
| Source revision | main |
| Source SHA-256 | 96477830ff58e3e64878f6e4030f71aa4d31ce92b9936d3bdead606fb0cc4fdd |
| Skippy ABI | 0.1.24 |
| Package manifest SHA-256 | 2ba6eea89f3cf26265535f97824a114590df186da14cd838906ce3ad2fec1c6c |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 2ba6eea89f3cf26265535f97824a114590df186da14cd838906ce3ad2fec1c6c |
| Metadata | shared/metadata.gguf | 0 tensors, 5.7 MB | e563f74f56f6fecbda245cf91597668e680fe65ba7df7f6b599842eb223ffa2b |
| Embeddings | shared/embeddings.gguf | 1 tensors, 955.6 MB | c16c74e5671c7ea9e18c84cf10d676aba48b3f975fce75e1205302cd2f86f68b |
| Output head | shared/output.gguf | 2 tensors, 955.6 MB | b9153ab015ee808059cea973f2ae5e7f9f504dcae516241ad7b54af55766d7c2 |
| Transformer layers | layers/layer-*.gguf | 73 layer artifacts, 724 tensors, 586.3 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/MiMo-V2.5-Pro-UD-Q4_K_XL-00001-of-00015.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_MiMo-V2.5-Pro-UD-Q4_K_XL-layers-193/package"
Links
- Source model: unsloth/MiMo-V2.5-Pro-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