Qwen 1 models
3 Qwen 1 models from Qwen on Hugging Face, from 7.7B to 72.3B parameters, published by Qwen in BF16, with a 32K-token context. The smallest official model, Qwen-7B, needs about 17.3 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Part of the Qwen series · Next generation: Qwen1.5
Pick a size
One row per official Qwen 1 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 |
|---|---|---|---|---|---|---|---|
| Qwen-7B-Chat | 7.7B | 17.3 GB | 8.6 GB | 4.3 GB | RTX A5000 | $0.176/hr | 16.0 GB |
| Qwen-72B | 72.3B | 162 GB | 80.8 GB | 40.4 GB | RTX A5000 × 7 | $1.23/hr | 80.0 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 (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Qwen-7B | 7.7B | BF16 | 17.3 GB | RTX A5000 | $0.176/hr |
| Qwen-7B-Chat | 7.7B | BF16 | 17.3 GB | RTX A5000 | $0.176/hr |
| Qwen-72B | 72.3B | BF16 | 162 GB | RTX A5000 × 7 | $1.23/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.
