GGUF layer package for running GLM-5.1-UD-Q3_K_S across a local Mesh LLM cluster.
This package is derived from meshllm/GLM-5.1-UD-Q3_K_S-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_S layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | meshllm/GLM-5.1-UD-Q3_K_S-GGUF |
| Model id | meshllm/GLM-5.1-UD-Q3_K_S-GGUF:UD-Q3_K_S |
| Family | GLM |
| Parameter scale | not recorded |
| Quantization | UD-Q3_K_S |
| Layer count | 79 |
| Activation width | 6144 |
| Package size | 337.4 GB |
| Source file | UD-Q3_K_S/GLM-5.1-UD-Q3_K_S-00001-of-00306.gguf |
| Package repo | meshllm/GLM-5.1-UD-Q3_K_S-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: meshllm/GLM-5.1-UD-Q3_K_S-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/GLM-5.1-UD-Q3_K_S-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": "meshllm/GLM-5.1-UD-Q3_K_S-GGUF:UD-Q3_K_S",
"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 | meshllm/GLM-5.1-UD-Q3_K_S-GGUF@main/UD-Q3_K_S/GLM-5.1-UD-Q3_K_S-00001-of-00306.gguf |
| Source revision | main |
| Source SHA-256 | 085cc9d78b83eaec1d556c6644e840c9e4e6eb4d370560f1e151fae873f2edee |
| Skippy ABI | 0.1.26 |
| Package manifest SHA-256 | 81d6e34fcaa61d6e11167c8d97e38dd18297678723041f717a08f3ce8002d51b |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 81d6e34fcaa61d6e11167c8d97e38dd18297678723041f717a08f3ce8002d51b |
| Metadata | shared/metadata.gguf | 0 tensors, 9.0 MB | 4427c9262ed6ed540b4b6b7541b41276f3fa7940d8d497bcfe1d91a39dd08d06 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 973.2 MB | 34b4d137908e325df2e6e0688f35b7a96b61dcfada4c1fc2514b5f9d55a2d3e4 |
| Output head | shared/output.gguf | 2 tensors, 1.8 GB | 1724fa1fec4c64aa89a29fba88c2231133db9ff21f90ba4008a07cebdc451844 |
| Transformer layers | layers/layer-*.gguf | 79 layer artifacts, 1806 tensors, 334.7 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-Q3_K_S/GLM-5.1-UD-Q3_K_S-00001-of-00306.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_GLM-5.1-UD-Q3_K_S-layers-200/package"
Links
- Source model: meshllm/GLM-5.1-UD-Q3_K_S-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