GGUF layer package for running Nemotron-3-Nano-30B-A3B-Q4_K_S across a local Mesh LLM cluster.
This package is derived from unsloth/Nemotron-3-Nano-30B-A3B-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_S layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | unsloth/Nemotron-3-Nano-30B-A3B-GGUF |
| Model id | unsloth/Nemotron-3-Nano-30B-A3B-GGUF:Q4_K_S |
| Family | Nemotron |
| Parameter scale | 30B-A3B |
| Quantization | Q4_K_S |
| Layer count | 52 |
| Activation width | 2688 |
| Package size | 20.9 GB |
| Source file | Nemotron-3-Nano-30B-A3B-Q4_K_S.gguf |
| Package repo | meshllm/Nemotron-3-Nano-30B-A3B-Q4_K_S-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/Nemotron-3-Nano-30B-A3B-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Nemotron-3-Nano-30B-A3B-Q4_K_S-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/Nemotron-3-Nano-30B-A3B-GGUF:Q4_K_S",
"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/Nemotron-3-Nano-30B-A3B-GGUF@main/Nemotron-3-Nano-30B-A3B-Q4_K_S.gguf |
| Source revision | main |
| Source SHA-256 | 40eb44a5d66ade97d17285aa9f9861a75f48a3bf5c3234bbba3b8f6a8190a076 |
| Skippy ABI | 0.1.25 |
| Package manifest SHA-256 | 33583c896e8c943cb16c6342e032a051997074091deb246dd134c3a523e48c09 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 33583c896e8c943cb16c6342e032a051997074091deb246dd134c3a523e48c09 |
| Metadata | shared/metadata.gguf | 0 tensors, 7.5 MB | 3b325d9cdb435c7e4985922d44d94d224d191f1b5a22d17702cb6492a4d32d87 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 238.5 MB | 867bb0d7c0cbbd52b2d35fea1dc056c91a6c6d67a531f3fcf493b92c3f7d3327 |
| Output head | shared/output.gguf | 2 tensors, 364.5 MB | f682184014fdaa077f3402716d36831736a3869871ddb5ca8c2f7ca559bfc1aa |
| Transformer layers | layers/layer-*.gguf | 52 layer artifacts, 398 tensors, 20.3 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/Nemotron-3-Nano-30B-A3B-Q4_K_S.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Nemotron-3-Nano-30B-A3B-Q4_K_S-layers-193/package"
Links
- Source model: unsloth/Nemotron-3-Nano-30B-A3B-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