GGUF layer package for running GLM-4.7-Flash-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/GLM-4.7-Flash-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-4.7-Flash-GGUF |
| Model id | unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL |
| Family | GLM |
| Parameter scale | not recorded |
| Quantization | UD-Q4_K_XL |
| Layer count | 47 |
| Activation width | 2048 |
| Package size | 16.7 GB |
| Source file | GLM-4.7-Flash-UD-Q4_K_XL.gguf |
| Package repo | meshllm/GLM-4.7-Flash-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-4.7-Flash-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/GLM-4.7-Flash-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-4.7-Flash-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-4.7-Flash-GGUF@main/GLM-4.7-Flash-UD-Q4_K_XL.gguf |
| Source revision | main |
| Source SHA-256 | b0d4fbc1211f891b4cfbf2a497160bfe06a49412420068904d426b7a13f4ba7f |
| Skippy ABI | 0.1.24 |
| Package manifest SHA-256 | 03bb2a103ca07cf560f8d7a6a086a6c5d8ea5481b2c01dbcd97b980bdf0abe71 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 03bb2a103ca07cf560f8d7a6a086a6c5d8ea5481b2c01dbcd97b980bdf0abe71 |
| Metadata | shared/metadata.gguf | 0 tensors, 9.0 MB | c19e16e61ba91e14f6b83775afd9e3674b793c9abb75aa168fb8536a7eaa57cc |
| Embeddings | shared/embeddings.gguf | 1 tensors, 179.1 MB | 16fb25aa8d9dfb63a4167565344c7d90b1a989af7630b751dca319f63d073db2 |
| Output head | shared/output.gguf | 2 tensors, 257.1 MB | 943d3043a429ca703c2ed9ccabd517169ce0628e1eda7f6dd7f33cee39ab08bf |
| Transformer layers | layers/layer-*.gguf | 47 layer artifacts, 841 tensors, 16.3 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/GLM-4.7-Flash-UD-Q4_K_XL.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_GLM-4.7-Flash-UD-Q4_K_XL-layers-197/package"
Links
- Source model: unsloth/GLM-4.7-Flash-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