GGUF layer package for running Qwen3-8B-Q4_K_M across a local Mesh LLM cluster.
This package is derived from unsloth/Qwen3-8B-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 | Q4_K_M layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | unsloth/Qwen3-8B-GGUF |
| Model id | unsloth/Qwen3-8B-GGUF |
| Family | Qwen3 |
| Parameter scale | 8B |
| Quantization | Q4_K_M |
| Layer count | 36 |
| Activation width | 4096 |
| Package size | 4.9 GB |
| Source file | Qwen3-8B-Q4_K_M.gguf |
| Package repo | meshllm/Qwen3-8B-Q4_K_M-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/Qwen3-8B-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Qwen3-8B-Q4_K_M-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/Qwen3-8B-GGUF",
"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/Qwen3-8B-GGUF@main/Qwen3-8B-Q4_K_M.gguf |
| Source revision | main |
| Source SHA-256 | 120307ba529eb2439d6c430d94104dabd578497bc7bfe7e322b5d9933b449bd4 |
| Skippy ABI | 0.1.22 |
| Package manifest SHA-256 | 7e3ecea929276d13b71a835ceee5cfccd2c075bd35f04a9e2bc7042c28bce0a6 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 7e3ecea929276d13b71a835ceee5cfccd2c075bd35f04a9e2bc7042c28bce0a6 |
| Metadata | shared/metadata.gguf | 0 tensors, 5.7 MB | 0f665e355aceb65f6187f2961a64febb626e4da4dff785f575745f2d4c935542 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 339.5 MB | 7bb6ba6790073cd060241136d8f0e4ba0665b887fbe7d1947bdcf7abda8605ae |
| Output head | shared/output.gguf | 2 tensors, 492.5 MB | 35393b015f2eea59d8652506d75455a306330c0e54a4ecf2d5de86559f150d56 |
| Transformer layers | layers/layer-*.gguf | 36 layer artifacts, 396 tensors, 4.1 GB | see model-package.json |
Validation
Generated by the Mesh LLM HF Jobs splitter from mesh-llm ref main and validated before upload:
skippy-model-package validate-package "/source/Qwen3-8B-Q4_K_M.gguf" "$PACKAGE_DIR"
Links
- Source model: unsloth/Qwen3-8B-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