1× DGX Spark
71.8tok/sEveryday
1 request, prose prompt (sampled, thinking off), with LiLiCorr (per recipe) Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- License unclear
Local AI · Recipe · 1× DGX Spark
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).
by vcruz305
Intelligence (original model) · Artificial Analysisno independent value
≤ 3 bit: quantization may cost quality
Engine
- 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
- Context
- 262,144
- Parameters
- 74B MoE / 9B aktiv (lt. Modellname)
- Creator
- vcruz305
- GitHub stars
- 0
- Repo updated
- Oct 16, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Decode · 1 request
Prefill by context
What you need
- Hardware
- 1 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsnvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB other
- Draft modelnvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr other
- Engine
- vLLM 0.32.0rc1.dev100+g77154ca61 (Wheel-Commit 77154ca6) + b12x 1.5.1, FlashInfer-Attention
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- ≤ 3 bit: quantization may cost qualityAt 3 bit and below the model may answer noticeably worse than the original. The intelligence number refers to the original.
- License unclear
Sources
- github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe#results
- github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe#measured-configurations
- github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe/blob/main/bench/receipts/dflash.json
- github.com/vcruz305/Nemotron-3.5-Bolt-74B-A9B-24GB-vLLM-recipe/blob/main/serve.sh
Related recipes
1× DGX Spark
60.3tok/sEveryday
1 request, prose prompt (essay), context 2k, no drafter (per recipe) Source
Intelligenceno independent value
- Custom kernel required
1× DGX Spark
59.4tok/sEveryday
1 request, chat prompt (20 prompts, thinking off), no drafting (default profile) Source
Intelligenceno independent value
- Custom kernel required
1× DGX Spark
58.3tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
- Custom kernel required
1× DGX Spark
55.6tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
1× DGX Spark
53.3tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
Local AI in your company?
In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.