---
type: "Article"
title: "Nemotron-3.5 30B NVFP4 with vLLM on 1× DGX Spark"
description: "Nemotron-3.5 30B NVFP4 with vLLM on 1× DGX Spark: recipe by sfxnz with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/sfxnz--nemotron-35-lightning-30b-a3b-1x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-01T20:41:14.881Z"
status: "stable"
---

# Nemotron-3.5 30B NVFP4 with vLLM on 1× DGX Spark

Nemotron-3.5 30B NVFP4 with vLLM on 1× DGX Spark: 93 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [sfxnz](https://www.contextstudios.ai/local-ai/creators/sfxnz.md)
- Engine: vLLM
- Quantization: NVFP4 (modelopt_mixed), FP8-KV, Marlin MoE, DSpark-3
- Model family: Nemotron-3.5
- Hardware: dgx-spark x1
- Context: 262144
- Artificial Analysis Intelligence Index: 12.9 ([source](https://artificialanalysis.ai/models/nemotron-3-5-lightning))

## All numbers

- 93 tok/s (Peak; Peak, 1 request, best value reported by source) — [source](https://github.com/sfxnz/Nemotron-3.5-Lightning-vLLM-DGX-Spark/blob/main/README.md)
- decode_tps: 93 (1 request) — [source](https://github.com/sfxnz/Nemotron-3.5-Lightning-vLLM-DGX-Spark/blob/main/README.md)
- prefill_tps: 678 (1 request) — [source](https://github.com/sfxnz/Nemotron-3.5-Lightning-vLLM-DGX-Spark/blob/main/README.md)
- ttft_ms: 246 (1 request) — [source](https://github.com/sfxnz/Nemotron-3.5-Lightning-vLLM-DGX-Spark/blob/main/README.md)

## Weights

- [nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4) (main, other)
- [nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark) (draft, other)

[https://github.com/sfxnz/Nemotron-3.5-Lightning-vLLM-DGX-Spark](https://github.com/sfxnz/Nemotron-3.5-Lightning-vLLM-DGX-Spark)

## Related

- [Local AI on your hardware.](https://www.contextstudios.ai/local-ai.md)
