2× DGX Spark
33tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence28with thinking
- No license
Local AI · Recipe · 2× DGX Spark
Inkling-Small 276B-A12B NVFP4 with SGLang on 2× DGX Spark
Inkling-Small 276B-A12B NVFP4 with SGLang on 2× DGX Spark: 33 tok/s according to github.com (dataset as of Nov 3, 2026).
by drowzeys
Engine
- Engine
- SGLang
- Quantization
- NVFP4 weights + NVFP4 KV (eigener Port)
- Model family
- Inkling-Small
- Context
- 1,048,576
- Parameters
- 276B MoE / 12B active
- Creator
- drowzeys
- GitHub stars
- 10
- Repo updated
- Aug 17, 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
What you need
- Hardware
- 2 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsthinkingmachines/Inkling-Small-NVFP4 Apache-2.0
- Draft modelRadixArk/Inkling-Small-DSpark-Preview License unclear
- Engine
- SGLang
- Context
- 1,048,576 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
- License unclear
Sources
Related recipes
2× DGX Spark
16tok/sPeak
1 request, mixed prompt set Source
Intelligence28with thinking
2× DGX Spark
no documented speed
Intelligence28with thinking
- Experimental
- License unclear
2× DGX Spark
89.3tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligenceno independent value
- Custom kernel required
- License unclear
2× DGX Spark
74tok/sEveryday
1 request, prose prompt (long story), thinking off, with MTP Source
Intelligence40with thinking
- Custom kernel required
- License unclear
2× DGX Spark
69.6tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- 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.