Loading…
Loading…
Models / Qwen3.5
4 models (0.8B to 9B) · ↓ 408K downloads a month · from $0.10/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalunsloth/Qwen3.5-0.8B | vLLM | 1.8 GB | 4.6 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalunsloth/Qwen3.5-2B | vLLM | 4.5 GB | 7.7 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalunsloth/Qwen3.5-4B | vLLM | 9.3 GB | 13.8 GB | $0.14/h RTX A4000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalunsloth/Qwen3.5-9B | vLLM | 19 GB | 24.9 GB | $0.34/h 2x RTX 5060 Ti |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").