QwQ models
2 QwQ models from Qwen on Hugging Face, from 32.8B to 32.8B parameters, published by Qwen in BF16, with contexts from 32K to 40K tokens. The smallest official model, QwQ-32B, needs about 73.2 GB of VRAM at its published precision; the cheapest live fit is A100 at $1.18/hr.
Pick a size
One row per official QwQ size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| QwQ-32B | 32.8B | 73.2 GB | 36.6 GB | 18.3 GB | A100 | $1.18/hr | 8.0 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| QwQ-32B | 32.8B | BF16 | 73.2 GB | A100 | $1.18/hr |
| QwQ-32B-Preview | 32.8B | BF16 | 73.2 GB | A100 | $1.18/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.