Loading…
Loading…
Models / Mixtral-8x7B
1 model (~46.7B) · ↓ 3.6K downloads a month · from $0.44/h on 2x RTX 3090 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 |
|---|---|---|---|---|
| GPTQ (TheBloke)TheBloke/Mixtral-8x7B-v0.1-GPTQ | vLLM | 24 GB | 29.9 GB | $0.44/h 2x RTX 3090 |
| Mixtral 8x7B Instruct v0.1 GPTQ (TheBloke)TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ | vLLM | 24 GB | 29.9 GB | $0.44/h 2x RTX 3090 |
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").