QwQ 32B Preview on NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 handles QwQ 32B Preview well at 24 tok/s at Q4_K_M. A solid choice for this model.
Model Size
32.5B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows QwQ 32B Preview performance at a different quality level on NVIDIA GeForce RTX 4090.
| 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 — 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
Source: 32B model performance extrapolation (2026-01-15)
Data last updated: 2026-03-01