8× RTX 3090
38.5tok/sPeak
1 request, mixed prompt set Source
Intelligenceno independent value
Local AI · Recipe · 8× RTX 3090
Qwen3.5-397B-A17B FP8 with vLLM on 8× RTX 3090
Qwen3.5-397B-A17B FP8 with vLLM on 8× RTX 3090: 62 tok/s according to huggingface.co (dataset as of Nov 3, 2026).
by 0xSero
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- vLLM 0.19.0
- Quantization
- W4A16 + FP8 KV
- Model family
- Qwen3.5-397B-A17B (REAP 264B)
- Context
- —
- Parameters
- 264B (REAP)
- Creator
- 0xSero
- GitHub stars
- 11
- Repo updated
- May 30, 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
- 8 × NVIDIA RTX 3090
- Weights
- Main weights0xSero/Qwen3.5-264B-W4A16 Apache-2.0
- Engine
- vLLM 0.19.0
Notes
What matters before you rebuild it.
- REAP-pruned
Sources
Related recipes
8× RTX 3090
13.9tok/sPeak
1 request, best value reported by source Source
Intelligence19with thinkingno thinking 15
- Experimental
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.