GGUF layer package for running Qwen3-0.6B-Q4_K_M across a local Mesh LLM cluster.
This package is derived from unsloth/Qwen3-0.6B-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/Qwen3-0.6B-GGUF |
| Model id | unsloth/Qwen3-0.6B-GGUF:Q4_K_M |
| Family | Qwen3 |
| Parameter scale | 0.6B |
| Quantization | Q4_K_M |
| Layer count | 28 |
| Activation width | 1024 |
| Package size | 548.1 MB |
| Source file | Qwen3-0.6B-Q4_K_M.gguf |
| Package repo | meshllm/Qwen3-0.6B-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/Qwen3-0.6B-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Qwen3-0.6B-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/Qwen3-0.6B-GGUF:Q4_K_M",
"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/Qwen3-0.6B-GGUF@main/Qwen3-0.6B-Q4_K_M.gguf |
| Source revision | main |
| Source SHA-256 | ac2d97712095a558e31573f62f466a3f9d93990898b0ec79d7c974c1780d524a |
| Skippy ABI | 0.1.24 |
| Package manifest SHA-256 | 7a45865de8c54aa7a27f4013957ce9b0fbd3f12b625dc1446ddc41d420bc4420 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 7a45865de8c54aa7a27f4013957ce9b0fbd3f12b625dc1446ddc41d420bc4420 |
| Metadata | shared/metadata.gguf | 0 tensors, 5.7 MB | dcce7cf2eb69714b43c0d035b92c7322978556d804e13d181f5fa13264d5d2de |
| Embeddings | shared/embeddings.gguf | 1 tensors, 127.4 MB | 3a5936cebcae465db29e43cc0b2b5259ea95d111bce53618b9d22f5536313d45 |
| Output head | shared/output.gguf | 1 tensors, 5.7 MB | 4627ae6766d652fe4de694e10e7a44916800f357d5b98eb3b21f9334d2aa1634 |
| Transformer layers | layers/layer-*.gguf | 28 layer artifacts, 308 tensors, 409.4 MB | 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/Qwen3-0.6B-Q4_K_M.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Qwen3-0.6B-Q4_K_M-layers-199/package"
Links
- Source model: unsloth/Qwen3-0.6B-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