Loading…
Loading…
Models / Qwen3.5
3 models (27B to 35B) · ↓ 68.2K downloads a month · from $0.38/h on 2x RTX 5060 Ti 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 |
|---|---|---|---|---|
| AWQ (QuantTrio)QuantTrio/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-AWQ | vLLM | 22 GB | 28.9 GB | $0.38/h 2x RTX 5060 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalJackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled | vLLM | 56 GB | 66.3 GB | $0.89/h 2x Nvidia A40 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalJackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled | vLLM | 72 GB | 82.9 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").