Loading…
Loading…
Models / phixtral-2x2_8
GPU memory needed (smallest version of each): phixtral-2x2_8 ~4.46B about 12.9 GB. The cheapest runs on RTX 4060 Ti from $0.17/h right now.
1 model (~4.46B) · ↓ 249 downloads a month · from $0.17/h on RTX 4060 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 |
|---|---|---|---|---|
| Originalmlabonne/phixtral-2x2_8 | vLLM | 8.9 GB | 12.9 GB | $0.17/h RTX 4060 Ti |
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").