1× DGX Spark
87.8tok/sPeak
1 request, synthetic prompt, with LiLiCorr/DFlash (per recipe) Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- License unclear
Local AI · Recipe · 1× DGX Spark
Nemotron-3.5-Bolt 74B-A9B 24GB pack with TensorFold on 1× DGX Spark
Nemotron-3.5-Bolt 74B-A9B 24GB pack with TensorFold on 1× DGX Spark: 71.8 tok/s according to github.com (dataset as of Nov 3, 2026).
by MiaAI-Lab
71.8tok/sEveryday
1 request, prose prompt (sampled, thinking off), with LiLiCorr (per recipe)
Source: github.comIntelligence (original model) · Artificial Analysisno independent value
≤ 3 bit: quantization may cost quality
Engine
- Engine
- TensorFold tensorfold-native v1.1.6 (eea9dc9c) + recipe patches/ (Bolt lane backend, libbolt.so CUDA forward pass), LiLiCorr drafts
- Quantization
- 24GB pack: IQ2_XXS experts (2.0625 bits), NVFP4 Mamba projections, Q8_0 attention/latent projections/lm_head; bf16 KV
- Model family
- Nemotron-3.5-Bolt-74B-A9B
- Context
- 262,144
- Parameters
- 74B MoE / 9B aktiv
- Creator
- MiaAI-Lab
- GitHub stars
- 11
- Repo updated
- Nov 1, 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
- TensorFold tensorfold-native v1.1.6 (eea9dc9c) + recipe patches/ (Bolt lane backend, libbolt.so CUDA forward pass), LiLiCorr drafts
- 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.
- Custom kernel required
- vision
- tool-calling
- License unclear
Sources
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.