Loading…
Loading…
Models / Qwen3.5
1 model (122B) · ↓ 115.4K downloads a month · from $0.89/h on 2x Nvidia A40 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 |
|---|---|---|---|---|
| Qwen3.5 122B A10B int4 fp8 hybrid (bleysg)bleysg/Qwen3.5-122B-A10B-int4-fp8-hybrid | vLLM | 71 GB | 82.2 GB | $0.89/h 2x Nvidia A40 |
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").