GGUF layer package for running NVIDIA-Nemotron-3-Ultra-550B-A55B-UD-Q4_K_S across a local Mesh LLM cluster.
This package is derived from unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-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_S layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF |
| Model id | unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:UD-Q4_K_S |
| Family | NVIDIA |
| Parameter scale | 550B-A55B |
| Quantization | UD-Q4_K_S |
| Layer count | 108 |
| Activation width | 8192 |
| Package size | 306.0 GB |
| Source file | UD-Q4_K_S/NVIDIA-Nemotron-3-Ultra-550B-A55B-UD-Q4_K_S-00001-of-00008.gguf |
| Package repo | meshllm/NVIDIA-Nemotron-3-Ultra-550B-A55B-UD-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/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/NVIDIA-Nemotron-3-Ultra-550B-A55B-UD-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/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:UD-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/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF@main/UD-Q4_K_S/NVIDIA-Nemotron-3-Ultra-550B-A55B-UD-Q4_K_S-00001-of-00008.gguf |
| Source revision | main |
| Source SHA-256 | 8aa4c9cc0044dee94902fded670a2e7be78fb8e6779265071c455fbe04af6112 |
| Skippy ABI | 0.1.25 |
| Package manifest SHA-256 | f0847d4be12e7584ea242982d2069efb9e223ffd89f928ddaeead2b20a9c71e9 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | f0847d4be12e7584ea242982d2069efb9e223ffd89f928ddaeead2b20a9c71e9 |
| Metadata | shared/metadata.gguf | 0 tensors, 7.5 MB | 9417802d01fa5719b276da2cdd30e0769ac8ddcc54e73f3a3052da2740e393b4 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 1.1 GB | 66d289c228129dac4a3958358354f076834160f56ce4022206546cc1e463c446 |
| Output head | shared/output.gguf | 2 tensors, 847.5 MB | 06fc88e0b37c68d096b23830cf4e46f4c1ad34f72c53de9ab15a490dbe7a2784 |
| Transformer layers | layers/layer-*.gguf | 108 layer artifacts, 924 tensors, 304.1 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/UD-Q4_K_S/NVIDIA-Nemotron-3-Ultra-550B-A55B-UD-Q4_K_S-00001-of-00008.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_NVIDIA-Nemotron-3-Ultra-550B-A55B-UD-Q4_K_S-layers-194/package"
Links
- Source model: unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-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