1× DGX Spark
26.6tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence21with thinkingno thinking 20
Local AI · Recipe · 1× RTX 5090
Qwen3.6-27B with NInfer on 1× RTX 5090
Qwen3.6-27B with NInfer on 1× RTX 5090: 186 tok/s according to github.com (dataset as of Nov 3, 2026).
by neroued
Intelligence (original model) · Artificial Analysis21with thinkingno thinking 20
Engine
- Engine
- NInfer main@bace20dc (2026-09-24)
- Quantization
- groupwise-int (.ninfer v3-Artefakt)
- Model family
- Qwen3.6-27B
- Context
- 262,144
- Parameters
- 27B dense
- Creator
- neroued
- GitHub stars
- 3,234
- Repo updated
- Nov 2, 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 RTX 5090
- Weights
- Main weightsneroued/Qwen3.6-27B-NInfer Apache-2.0
- Engine
- NInfer main@bace20dc (2026-09-24)
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
Sources
Related recipes
1× RTX 5090
252tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
1× RTX 5090
128tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
1× RTX 5090
122tok/sMixed
1 request, llama-benchy 2048-token prompt, 128 tokens out, depth 0, with MTP Source
Intelligence34with thinkingno thinking 20
1× RTX 5090
780tok/sPeak
1 request, JSON prompt Source
Intelligence18with thinkingno thinking 15
- Custom kernel required
1× RTX 5090
367tok/sPeak
1 request, synthetic prompt Source
Intelligence9with thinking
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.