QwenQwQ 32B Preview on NVIDIA GeForce RTX 4090
Yes — RTX 4090 handles QwQ 32B Preview well at Q4_K_M — 24 tok/s. Solid daily-driver performance on 24 GB VRAM.
Model Size
32.5B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantization
Q4_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for QwQ 32B Preview on NVIDIA GeForce RTX 4090 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 | 24 tok/s | 380ms | ✓ Yes | Good | estimated |
Notes
Q4_K_M
Q4 at 18.4GB fits on 4090 with 5.6GB headroom. Reasoning responses are long (chain-of-thought) so tok/s matters. Good but not fast.
About QwQ 32B Preview
QwQ 32B Preview (32.5B) is a reasoning, coding, ai coding, ai building model. Reasoning-focused model that uses chain-of-thought natively. Builders pair this with a coding model for complex architecture decisions. Approaches o1-mini on reasoning benchmarks. Same size as Qwen 2.5 Coder 32B, so they compete for VRAM; run one at a time, not concurrently.
View all QwQ 32B Preview hardware options →About NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Estimate method: 32B model performance extrapolation. Reference hardware source: github.com (2026-01-15)
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.