§01·compatibility · /check
Qwen3 30B-A3B on RTX 5090
Yes — Qwen3 30B-A3B runs on the RTX 5090 (32 GB). Fastest community-measured result: 7093 prefill tokens/s.
✓ runsllmactive50 series32GB VRAM
§02·benchmarks
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| llm | Q4_K | 7093prefill tokens/s | ✓ | hardware-corner.net· web | 2026-05-15 | ||
| llm | Q4_K | 226.1tokens/s | ✓ | hardware-corner.net· web | 2026-05-15 |
§03·common questions
Can you run Qwen3 30B-A3B on RTX 5090?
Yes — Qwen3 30B-A3B runs on the RTX 5090 (32 GB). Fastest community-measured result: 7093 prefill tokens/s.
Which quantizations have been tested for Qwen3 30B-A3B on RTX 5090?
Q4_K — measured in community benchmarks.
How fast is Qwen3 30B-A3B on RTX 5090?
Up to 7093 prefill tokens/s (llm), the fastest community-measured result.
Are there step-by-step instructions for Qwen3 30B-A3B on RTX 5090?
Yes — a step-by-step recipe documents Qwen3 30B-A3B on the RTX 5090; see the recipes listed below.
§04·related recipes
- llmintermediate19GB+
Qwen3-30B-A3B on RTX 5090: 226 tok/s MoE Chat with Room to Spare
- llmintermediate24GB+
Qwen3-30B-A3B on RTX 3090 Ti: 167 tok/s MoE Chat That Fits the Full 24 GB Card
- llmintermediate24GB+
Qwen3-30B-A3B on RTX 3090: Full-GPU MoE Chat at 153 tok/s
- llmintermediate12GB+
Qwen3-30B-A3B on RTX 4070: Local MoE LLM via CPU-Offload