GGUF layer package for running GLM-5.1-UD-Q3_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/GLM-5.1-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-Q3_K_XL layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | unsloth/GLM-5.1-GGUF |
| Model id | unsloth/GLM-5.1-GGUF:UD-Q3_K_XL |
| Family | GLM |
| Parameter scale | not recorded |
| Quantization | UD-Q3_K_XL |
| Layer count | 79 |
| Activation width | 6144 |
| Package size | 317.5 GB |
| Source file | UD-Q3_K_XL/GLM-5.1-UD-Q3_K_XL-00001-of-00008.gguf |
| Package repo | meshllm/GLM-5.1-UD-Q3_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/GLM-5.1-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/GLM-5.1-UD-Q3_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/GLM-5.1-GGUF:UD-Q3_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/GLM-5.1-GGUF@main/UD-Q3_K_XL/GLM-5.1-UD-Q3_K_XL-00001-of-00008.gguf |
| Source revision | main |
| Source SHA-256 | cfc509768323e6fa326f137a6fb0e553ad378e4b27ed8dea2261ce11fce704af |
| Skippy ABI | 0.1.27 |
| Package manifest SHA-256 | 666156eb033f3f356b598f45625516f8b577d7a3f60e2bbba979bf8e195eeb3a |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 666156eb033f3f356b598f45625516f8b577d7a3f60e2bbba979bf8e195eeb3a |
| Metadata | shared/metadata.gguf | 0 tensors, 9.0 MB | 33e4da154047bd3053ac852c86968429c540e4a11ab61f2b3731d06109216ff3 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 973.2 MB | b5cde1dc307f6beb092eff4096e06bdc1a5dfc1545ca6a5d1eb1b5d24afb20e9 |
| Output head | shared/output.gguf | 2 tensors, 753.4 MB | 2f8a04288e0f1f565e79c0a6cd431d8ea06bc37c5bcd499bf1eac0dc9e809ee6 |
| Transformer layers | layers/layer-*.gguf | 79 layer artifacts, 1806 tensors, 315.8 GB | see model-package.json |
Validation
Generated by the Mesh LLM HF Jobs splitter from mesh-llm ref 79f6bc603c74d9335087fa08f06d14d21fa99f33.
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-Q3_K_XL/GLM-5.1-UD-Q3_K_XL-00001-of-00008.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_GLM-5.1-UD-Q3_K_XL-layers-200/package"
Links
- Source model: unsloth/GLM-5.1-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