zianglih models
1 zianglih model on Hugging Face, from 50.6B to 50.6B parameters. The cheapest way to run JoyAI-LLM-Flash-MXFP8-last-6-BF16 is $1.38/hr.
zianglih models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| JoyAI-LLM-Flash-MXFP8-last-6-BF16 | 50.6B | F8_E4M3 | 56.5 GB | RTX PRO 6000 | $1.38/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
