Loading…
Loading…
Models / Qwen3.8
1 model (27B) · ↓ 26.1K downloads a month · from $0.46/h on RTX A6000 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/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 | vLLM | 56 GB | 66.3 GB | $0.74/h 4x RTX 3090 |
| Qwen3.8 27B AEON ULTIMATE UNCENSORED NVFP4 MIXEDAEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4-MIXED | vLLM | 25 GB | 32 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").