GGUF layer package for running Kimi-K2.5-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Kimi-K2.5-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/Kimi-K2.5-GGUF |
| Model id | unsloth/Kimi-K2.5-GGUF:UD-Q4_K_XL |
| Family | Kimi |
| Parameter scale | not recorded |
| Quantization | UD-Q4_K_XL |
| Layer count | 61 |
| Activation width | 7168 |
| Package size | 579.7 GB |
| Source file | UD-Q4_K_XL/Kimi-K2.5-UD-Q4_K_XL-00001-of-00013.gguf |
| Package repo | meshllm/Kimi-K2.5-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/Kimi-K2.5-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Kimi-K2.5-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/Kimi-K2.5-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/Kimi-K2.5-GGUF@ef35f0cc9d9ac0781e716e0fd64214626457de85/UD-Q4_K_XL/Kimi-K2.5-UD-Q4_K_XL-00001-of-00013.gguf |
| Source revision | ef35f0cc9d9ac0781e716e0fd64214626457de85 |
| Source SHA-256 | 848fffb3ac4b5da143119ee75cb8aaf58dfb48b162b4944e2dd382462684b111 |
| Skippy ABI | 0.1.22 |
| Package manifest SHA-256 | 0b37305d9dba8dff1c54b39bf4f53a9d0d4b0a2a91682045eccd1ab8c6d38f6b |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 0b37305d9dba8dff1c54b39bf4f53a9d0d4b0a2a91682045eccd1ab8c6d38f6b |
| Metadata | shared/metadata.gguf | 0 tensors, 6.6 MB | 9ea05bdc559d2618a45053b59cf6ca843ca5de46455a8ee2217587eb93949fca |
| Embeddings | shared/embeddings.gguf | 1 tensors, 636.6 MB | fb4d8cabfcb926ed1e8482b6e15b6a7181a5217dc2f596319a3fe85f2f2b7e0b |
| Output head | shared/output.gguf | 2 tensors, 925.4 MB | 4b1e609106802f3afef0ae37c76af4ba856d9a747d48a7459970f3507e4a0544 |
| Transformer layers | layers/layer-*.gguf | 61 layer artifacts, 1093 tensors, 578.2 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/Kimi-K2.5-UD-Q4_K_XL-00001-of-00013.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Kimi-K2.5-UD-Q4_K_XL-layers-197/package"
Links
- Source model: unsloth/Kimi-K2.5-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