GPUFits
Can RTX 4090 run Qwen3 32B?
⚠️ Tight
Qwen3 32B @ Q4_K_M · 8K context
Needed
23.7 GB
Usable
24.0 GB
VRAM breakdown
| Weights (Q4_K_M) | 20.1 GB |
| KV cache (8K context) | 2.1 GB |
| Runtime overhead | 1.5 GB |
| Total | 23.7 GB |
Computed at 8K context with fp16 KV cache. Longer contexts need more VRAM — use the VRAM calculator for other settings.
Recommended quantization
Q4_K_M
Estimated generation speed
~38 tok/s @ Q4_K_M
Theoretical estimates based on published architecture data and measured GGUF sizes; real-world speed varies ±30%.
Smaller models this GPU runs well
FAQ
- How much VRAM does Qwen3 32B need?
- At Q4_K_M with 8K context: 20.1GB weights + 2.1GB KV cache + 1.5GB runtime overhead = 23.7GB total. RTX 4090 offers 24.0GB usable VRAM, so the verdict is: Tight fit.
- What is the best quantization for Qwen3 32B on RTX 4090?
- Q4_K_M — the highest tier that still fits within 24.0GB usable VRAM at 8K context. Lower tiers (Q3/Q2) fit too but cost noticeable quality.
- How fast does Qwen3 32B run on RTX 4090?
- About 38 tokens/s at Q4_K_M (theoretical estimate, ±30% in real-world use).
Check another combination in the GPU Checker →
Data verified 2026-08-04