---
type: "Article"
title: "Nemotron 3.5 Bolt 74B-A9B IQ2 with vLLM on 1× DGX Spark"
description: "Nemotron 3.5 Bolt 74B-A9B IQ2 with vLLM on 1× DGX Spark: recipe by vcruz305 with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/vcruz305--nemotron-3.5-bolt-74b-a9b-iq2-1spark-vllm-dflash"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:30:18.507Z"
status: "stable"
---

# Nemotron 3.5 Bolt 74B-A9B IQ2 with vLLM on 1× DGX Spark

Nemotron 3.5 Bolt 74B-A9B IQ2 with vLLM on 1× DGX Spark: 87.8 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [vcruz305](https://www.contextstudios.ai/local-ai/creators/vcruz305.md)
- Engine: vLLM 0.32.0rc1.dev100+g77154ca61 (Wheel-Commit 77154ca6) + b12x 1.5.1, FlashInfer-Attention
- Quantization: ModelOpt IQ2 gemischt (IQ2_XXS + ausgewählte Q8_0/NVFP4/unquantisierte Tensoren, 24 GB), FP8-KV; Draft LiLiCorr NVFP4 (DFlash, 7 Tokens)
- Model family: Nemotron-3.5-Bolt-74B-A9B
- Hardware: dgx-spark x1
- Context: 262144

## All numbers

- 87.8 tok/s (Peak; Peak, 1 request, synthetic prompt, with LiLiCorr/DFlash (per recipe)) — [source](https://github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe#results)
- decode_tps: 87.82 (1 request) — [source](https://github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe#results)
- prefill_tps: 1327.53 (1 request) — [source](https://github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe#results)

## Weights

- [nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB) (main, other)
- [nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr) (draft, other)

[https://github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe](https://github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe)

## Related

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