QwenQwen3-32B Instruct on NVIDIA GeForce RTX 5090
Yes — RTX 5090 runs Qwen3-32B Instruct excellently at Q4_K_M — 44 tok/s. 32 GB VRAM with plenty of headroom.
Model Size
32B
Device VRAM
32 GB
Bandwidth
1792 GB/s
Quantization
Q4_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Qwen3-32B Instruct on NVIDIA GeForce RTX 5090 at Q4_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q4_K_M | 44 tok/s | – | ✓ Yes | Excellent | benchmarked |
Notes
Q4_K_M
32GB GDDR7 fits Q4_K_M fully in VRAM. External benchmark reports 61.4 tok/s at 4K, 50.9 at 16K, and 43.8 at 32K context.
About Qwen3-32B Instruct
Qwen3-32B Instruct (32B) is a chat, coding, ai coding, reasoning, multi-purpose model. Qwen 3 dense 32B instruct for high-quality local inference where VRAM allows; 32K default and 128K max context. Apache 2.0.
View all Qwen3-32B Instruct hardware options →About NVIDIA GeForce RTX 5090
NVIDIA GeForce RTX 5090 has 32 GB at 1792 GB/s. Street price: $2,199.
See all models NVIDIA GeForce RTX 5090 can run →Builds with NVIDIA GeForce RTX 5090
Source: Hardware Corner measured Qwen3 32B (Q4_K) token generation on RTX 5090: 43.8 tok/s at 32K context (2026-04-11)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.