GGUF layer package for running Kimi-K2.7-Code-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Kimi-K2.7-Code-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-K2.7-Code-GGUF |
| Model id | unsloth/Kimi-K2.7-Code-GGUF:UD-Q4_K_XL |
| Family | Kimi |
| Parameter scale | not recorded |
| Quantization | UD-Q4_K_XL |
| Layer count | 61 |
| Activation width | 7168 |
| Package size | 544.0 GB |
| Source file | UD-Q4_K_XL/Kimi-K2.7-Code-UD-Q4_K_XL-00001-of-00014.gguf |
| Package repo | meshllm/Kimi-K2.7-Code-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-K2.7-Code-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Kimi-K2.7-Code-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-K2.7-Code-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-K2.7-Code-GGUF@main/UD-Q4_K_XL/Kimi-K2.7-Code-UD-Q4_K_XL-00001-of-00014.gguf |
| Source revision | main |
| Source SHA-256 | 65f0aca336f876902323a90e2aff32cac76d071b2cdd818c6a8d78be8fc2c680 |
| Skippy ABI | 0.1.26 |
| Package manifest SHA-256 | f091c5b171e113fbaf54c7a77264b62e2940887c9ce436b0c3f72c9d981cf39f |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | f091c5b171e113fbaf54c7a77264b62e2940887c9ce436b0c3f72c9d981cf39f |
| Metadata | shared/metadata.gguf | 0 tensors, 6.6 MB | 18cf1a16577311975d58524344203f54b2edb61e086581699f0c2a2c658147e0 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 1.2 GB | 66368df5cf3f85a7a14fddafe1817a4c0bae08b204f9e7ee4171c6379a9272fb |
| Output head | shared/output.gguf | 2 tensors, 1.2 GB | 88119cba4f946a2ad3cc15e62a2bc304cd1a302b53f1ebf15561eaa92fb8fc55 |
| Transformer layers | layers/layer-*.gguf | 61 layer artifacts, 1093 tensors, 541.7 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-K2.7-Code-UD-Q4_K_XL-00001-of-00014.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Kimi-K2.7-Code-UD-Q4_K_XL-layers-192/package"
Links
- Source model: unsloth/Kimi-K2.7-Code-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