1 request, best value reported by source Source
Local AI · Recipe · 1× DGX Spark
Ornith-1.5 35B NVFP4 with SGLang on 1× DGX Spark
Ornith-1.5 35B NVFP4 with SGLang on 1× DGX Spark: 74.9 tok/s according to github.com (dataset as of Nov 3, 2026).
by vcruz305
Engine
- Engine
- SGLang / vLLM SGLang 0.5.18.dev760 / vLLM g75231eff2
- Quantization
- NVFP4 (ModelOpt, 21.4 GB)
- Model family
- Ornith-1.5
- Context
- 262,144
- Parameters
- ~35B MoE / ~3B active
- Creator
- vcruz305
- GitHub stars
- 3
- Repo updated
- Aug 27, 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 weightsornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIT
- othervcruz305/Ornith-1.5-35B-A3B-GGUF License unclear
- Engine
- SGLang / vLLM SGLang 0.5.18.dev760 / vLLM g75231eff2
- Context
- 262,144 tokens
Related recipes
no documented speed
1 request, prose prompt (sampled, thinking off), with LiLiCorr (per recipe) Source
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- License unclear
1 request, prose prompt (essay), context 2k, no drafter (per recipe) Source
- Custom kernel required
1 request, chat prompt (20 prompts, thinking off), no drafting (default profile) Source
- Custom kernel required
1 request, prose prompt, with DFlash2 (per recipe) Source
- Custom kernel required
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.