1× RTX 5090
252tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
Local AI · Recipe · 2× RTX PRO 6000
Qwen3.6 27B BF16 with vLLM on 2× RTX PRO 6000
Qwen3.6 27B BF16 with vLLM on 2× RTX PRO 6000: 90.9 tok/s according to github.com (dataset as of Nov 3, 2026).
by jcartu
Intelligence (original model) · Artificial Analysis21with thinkingno thinking 20
Engine
- Engine
- vLLM repne/vllm:v13
- Quantization
- BF16 (unquantisiert)
- Model family
- Qwen3.6
- Context
- 134,144
- Parameters
- 27B dense
- Creator
- jcartu
- GitHub stars
- 7
- Repo updated
- Jun 3, 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 RTX PRO 6000 Blackwell
- Weights
- Main weightsQwen/Qwen3.6-27B Apache-2.0
- Draft modelz-lab/Qwen3.6-27B-DFlash MIT
- Engine
- vLLM repne/vllm:v13
- Context
- 134,144 tokens
Related recipes
2× RTX 5090
249tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
- License unclear
2× RTX 3090
179tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
- License unclear
2× RTX 5090
168tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligence21with thinkingno thinking 20
2× RTX 5090
153tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
1× RTX 5090
128tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
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.