GLM-5.2-UD-Q4_K_XL
Distributed GGUF inference package for Mesh LLM
GGUF layer package for running GLM-5.2-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/GLM-5.2-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/GLM-5.2-GGUF |
| Model id | unsloth/GLM-5.2-GGUF:UD-Q4_K_XL |
| Family | GLM |
| Parameter scale | not recorded |
| Quantization | UD-Q4_K_XL |
| Layer count | 79 |
| Activation width | 6144 |
| Package size | 435.9 GB |
| Source file | UD-Q4_K_XL/GLM-5.2-UD-Q4_K_XL-00001-of-00011.gguf |
| Package repo | meshllm/GLM-5.2-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/GLM-5.2-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/GLM-5.2-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/GLM-5.2-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/GLM-5.2-GGUF@main/UD-Q4_K_XL/GLM-5.2-UD-Q4_K_XL-00001-of-00011.gguf |
| Source revision | main |
| Source SHA-256 | 3256ac8c290273f0965ff39e93a8bcd07dc99bcd23e923bd4b7306ef39061038 |
| Skippy ABI | 0.1.27 |
| Package manifest SHA-256 | 02e3510e6674aad532aa21824abf2d2eace783c416cd07d648ab74c517f5e729 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 02e3510e6674aad532aa21824abf2d2eace783c416cd07d648ab74c517f5e729 |
| Metadata | shared/metadata.gguf | 0 tensors, 9.0 MB | 34bb694f1752b0c272e3b4f7a2c656e17803cf3593f9cee3426a2718895d9235 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 973.2 MB | 9e5a5f164e0510439ce02ca3523886156e7c14ed3be580656851f9a9d4b79aad |
| Output head | shared/output.gguf | 2 tensors, 973.2 MB | 3f6ecf9daa9157864dc85d9d3ebdeef5bb9a68c75d689f02020aede13c536b83 |
| Transformer layers | layers/layer-*.gguf | 79 layer artifacts, 1806 tensors, 434.0 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/GLM-5.2-UD-Q4_K_XL-00001-of-00011.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_GLM-5.2-UD-Q4_K_XL-layers-201/package"
Links
- Source model: unsloth/GLM-5.2-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