GLM-5.2-Q2_K-MTP-Q8
Distributed GGUF inference package for Mesh LLM
GGUF layer package for running GLM-5.2-Q2_K-MTP-Q8 across a local Mesh LLM cluster.
This package is derived from meshllm/GLM-5.2-Q2_K-MTP-Q8-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 | Q2_K layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | meshllm/GLM-5.2-Q2_K-MTP-Q8-GGUF |
| Model id | meshllm/GLM-5.2-Q2_K-MTP-Q8-GGUF:Q2_K-MTP-Q8 |
| Family | GLM |
| Parameter scale | not recorded |
| Quantization | Q2_K |
| Layer count | 79 |
| Activation width | 6144 |
| Package size | 260.3 GB |
| Source file | Q2_K-MTP-Q8/GLM-5.2-Q2_K-MTP-Q8-00001-of-00306.gguf |
| Package repo | meshllm/GLM-5.2-Q2_K-MTP-Q8-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-5.2-Q2_K-MTP-Q8-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/GLM-5.2-Q2_K-MTP-Q8-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-5.2-Q2_K-MTP-Q8-GGUF:Q2_K-MTP-Q8",
"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-5.2-Q2_K-MTP-Q8-GGUF@main/Q2_K-MTP-Q8/GLM-5.2-Q2_K-MTP-Q8-00001-of-00306.gguf |
| Source revision | main |
| Source SHA-256 | 6e1841a844cae68f434d7f699e1e974232a687e700ad7b26631d6880eb541b9a |
| Skippy ABI | 0.1.27 |
| Package manifest SHA-256 | 0df2893e5d1e553b9901c944d0ceae959ee69a949d8a2e69c645f8cae3d91257 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 0df2893e5d1e553b9901c944d0ceae959ee69a949d8a2e69c645f8cae3d91257 |
| Metadata | shared/metadata.gguf | 0 tensors, 9.0 MB | d239e9f5bb3151e29fa2f1f55c53eff16af5737e06afe541c6f24016d74bc8d6 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 973.2 MB | f5694c010726da17a33d68e0bf91566b91f9ccc9bfc08da393faf4c6cfa545b2 |
| Output head | shared/output.gguf | 2 tensors, 1.8 GB | b2e3fb2597217dd42464a10c02ec9a866571b37ea61c59d59a9ac84e29db6e50 |
| Transformer layers | layers/layer-*.gguf | 79 layer artifacts, 1521 tensors, 257.6 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/Q2_K-MTP-Q8/GLM-5.2-Q2_K-MTP-Q8-00001-of-00306.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_GLM-5.2-Q2_K-MTP-Q8-layers-193/package"
Links
- Source model: meshllm/GLM-5.2-Q2_K-MTP-Q8-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