QwQ-32B
QwQ-32B is an open-weights language model from Qwen, released March 5, 2025. It has 32B parameters (dense). On the Epoch Capabilities Index it scores 136.5, rank 135 of 256 rated models.
Check it against your own PC →
Can you run QwQ-32B locally?
The smallest common GPU it runs on is 16 GB of VRAM (with 32 GB of RAM): Q3_K_M, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 5.2 GB | 11.0 GB | ~3 |
| 8 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 7.2 GB | 9.0 GB | ~3 |
| 12 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 11.2 GB | 5.0 GB | ~5 |
| 16 GB VRAM | Runs, slowly | Q3_K_M (okay) | 15.2 GB | 4.4 GB | ~5 |
| 24 GB VRAM | Runs on GPU | IQ4_XS (good) | 21.0 GB | – | ~32 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 30.2 GB | – | ~39 |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 59.1% |
| GPQA Diamond | 56.0% |
| Aider Polyglot | 20.9% |
Links
Models with a similar score
gpt-oss-120b · Grok-3 mini · Qwen3.5-9B · GPT-5 nano · DeepSeek-R1 · Qwen3-235B-A22B · Qwen3-30B-A3B-Thinking (Jul 2025) · Qwen3-235B-A22B-Instruct (Jul 2025)
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash