Loading…
Loading…
Models / Qwen3.6
1 model (27B) · ↓ 156.3K 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 |
|---|---|---|---|---|
| OriginalAEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 | vLLM | 56 GB | 66.3 GB | $0.89/h 2x Nvidia A40 |
| Qwen3.6 27B AEON Ultimate Uncensored Multimodal NVFP4 MTP XSAEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS | vLLM | 21 GB | 27.5 GB | $0.38/h 2x RTX 5060 Ti |
| Qwen3.6 27B AEON Ultimate Uncensored Multimodal NVFP4 MTPAEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP | vLLM | 29 GB | 36.3 GB | $0.46/h RTX A6000 |
| Qwen3.6 27B AEON Ultimate Uncensored NVFP4AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 | vLLM | 28 GB | 35.4 GB | $0.46/h RTX A6000 |
| Qwen3.6 27B AEON Ultimate Uncensored Text NVFP4 MTP XSAEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Text-NVFP4-MTP-XS | vLLM | 20 GB | 26.4 GB | $0.38/h 2x RTX 5060 Ti |
| Qwen3.6 27B AEON Ultimate Uncensored Text NVFP4 MTPAEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Text-NVFP4-MTP | vLLM | 28 GB | 35.3 GB | $0.46/h RTX A6000 |
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").