Views
No views yet
| Base model | — |
| Format | BF16 |
| Total params | 337B |
| Active / token | — |
| Experts / layer | 216 |
| Layers | 60 |
| Hidden size | 3072 |
| Context | 262,144 |
| On-disk size | 675 GB |
| Variant | Format | Link |
|---|---|---|
Trinity-337B (this) | BF16 | link |
Trinity-337B-W4A16 | W4A16 | link |
Trinity-337B-W4A16-192 | W4A16 | link |
1@misc{lasby2025reap,
2 title = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
3 author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
4 year = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
5}