DeepSeek R1 Distill Qwen 32B on NVIDIA GeForce RTX 5090
NVIDIA GeForce RTX 5090 runs DeepSeek R1 Distill Qwen 32B excellently at 42 tok/s at Q5_K_M. This is a strong pairing.
Model Size
32.5B
Device VRAM
32 GB
Bandwidth
1792 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows DeepSeek R1 Distill Qwen 32B performance at a different quality level on NVIDIA GeForce RTX 5090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 42 tok/s | 220ms | ✓ Yes | Excellent | estimated |
Notes
Q5_K_M
Q5 32B reasoning fits on 32GB. Best local reasoning performance.
About DeepSeek R1 Distill Qwen 32B
DeepSeek R1 Distill Qwen 32B (32.5B) is a reasoning, coding, chat model. Distilled reasoning model with strong coding and chat capabilities.
View all DeepSeek R1 Distill Qwen 32B 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: Community benchmarks and estimated performance (2026-03-01)
Data last updated: 2026-03-15