§01·compatibility · /check
Qwen3.5 35B on RTX 5090
Yes — Qwen3.5 35B runs on the RTX 5090 (32 GB). Fastest community-measured result: 6605.2 prefill tokens/s.
✓ runsmultimodalactive50 series32GB VRAM
step-by-step recipe for this pair
Qwen3.5-35B-A3B on RTX 5090: Blackwell MXFP4 MoE Chat at 165 tok/s
multimodalintermediate24GB+
§02·benchmarks
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| llm | MXFP4 | 6605.2prefill tokens/s | ✓ | hardware-corner.net· web | 2026-05-15 | ||
| llm | MXFP4 | 165.2tokens/s | ✓ | hardware-corner.net· web | 2026-05-15 |
§03·more Qwen3.5 35B recipes
§04·common questions
Can you run Qwen3.5 35B on RTX 5090?
Yes — Qwen3.5 35B runs on the RTX 5090 (32 GB). Fastest community-measured result: 6605.2 prefill tokens/s.
Which quantizations have been tested for Qwen3.5 35B on RTX 5090?
MXFP4 — measured in community benchmarks.
How fast is Qwen3.5 35B on RTX 5090?
Up to 6605.2 prefill tokens/s (llm), the fastest community-measured result.
Are there step-by-step instructions for Qwen3.5 35B on RTX 5090?
Yes — a step-by-step recipe documents Qwen3.5 35B on the RTX 5090, linked at the top of this page.