| ▲ | rew0rk 2 days ago | |
Looking at HF, it looks like the unquantized version is half the size of glm-5.2 756 GB vs 1.51 TB. I wonder how they were able to optimize it this well | ||
| ▲ | dannyw 2 days ago | parent | next [-] | |
FP8 experts not BF16. | ||
| ▲ | jauntywundrkind 2 days ago | parent | prev [-] | |
FP8 vs BF16. But yeah, nice job. | ||