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-Lightning-30B-A3B IQ4_NL with llama.cpp on 1× DGX Spark
Nemotron-3.5-Lightning-30B-A3B IQ4_NL with llama.cpp on 1× DGX Spark: 113 tok/s according to huggingface.co (dataset as of Nov 3, 2026).
by vcruz305
Intelligence (original model) · Artificial Analysis13with thinking
≤ 3 bit: quantization may cost quality
Engine
- Engine
- llama.cpp b1-70dfba5
- Quantization
- GGUF Q4_0 (empfohlen); IQ4_NL, MXFP4_MOE, Q5_0, Q8_0, Mixed Q2_0/Q4_0
- Model family
- Nemotron-3.5-Lightning-30B-A3B
- Context
- —
- Parameters
- 30B total / 3B active
- Creator
- vcruz305
- GitHub stars
- 5
- Repo updated
- Aug 11, 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 weightsvcruz305/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF other
- Basenvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 other
- Engine
- llama.cpp b1-70dfba5
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
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.