Views
No views yet
| 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 |
| Property | Value |
|---|---|
| Source model | unsloth/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF |
| Model id | unsloth/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:UD-Q4_K_XL |
| Family | NVIDIA |
| Parameter scale | 30B-A3B |
| Quantization | UD-Q4_K_XL |
| Layer count | 52 |
| Activation width | 2688 |
| Package size | 22.7 GB |
| Source file | NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-UD-Q4_K_XL.gguf |
| Package repo | meshllm/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-UD-Q4_K_XL-layers |
1# Run this on each machine that should contribute memory/compute.
2mesh-llm serve --model "meshllm/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-UD-Q4_K_XL-layers" --split1# Check the mesh and discover the OpenAI-compatible model name.
2curl -s http://localhost:3131/api/status
3curl -s http://localhost:3131/v1/models1# Send an OpenAI-compatible chat request.
2curl -s http://localhost:3131/v1/chat/completions \
3 -H "Content-Type: application/json" \
4 -d '{
5 "model": "unsloth/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:UD-Q4_K_XL",
6 "messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
7 "max_tokens": 128
8 }'| Property | Value |
|---|---|
| Format | layer-package |
| Canonical source ref | unsloth/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF@main/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-UD-Q4_K_XL.gguf |
| Source revision | main |
| Source SHA-256 | 82eb2c0a47383fc0d59d06faf0b60ad0ff0d566b8d403047525e751824e077ea |
| Skippy ABI | 0.1.24 |
| Package manifest SHA-256 | 450f4df4c4c88248bf3bd5ee981fba7a6bdfefeffd70620828b04f0988a576d0 |
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 450f4df4c4c88248bf3bd5ee981fba7a6bdfefeffd70620828b04f0988a576d0 |
| Metadata | shared/metadata.gguf | 0 tensors, 7.5 MB | 7c0f4fddaa6bdfc537a09d440f78992877d86ae1907f5199b9f5acdfce838b25 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 364.5 MB | b75bebda3b99495917340bd0fdb1c2794f494dbd6d8acfba47cf98f5160bbe32 |
| Output head | shared/output.gguf | 2 tensors, 364.5 MB | 063b88dad92ae63481020a91c4853984d1eb73c1ed37a8f43086c11c5c203446 |
| Transformer layers | layers/layer-*.gguf | 52 layer artifacts, 398 tensors, 22.0 GB | see model-package.json |
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/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-UD-Q4_K_XL.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-UD-Q4_K_XL-layers-193/package"