Can I run bloomz-560m on an RTX 3060 12 GB?
Yes
Its published weights (1.12 GB) fit in the 10.8 GB an RTX 3060 12 GB can use, with room for an unknown amount of context.
hf download bigscience/bloomz-560mFiles and context on RTX 3060 12 GB
Each file of bloomz-560m (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On RTX 3060 12 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 1.12 GB | Fits | not known | not known |
| 4-bit (estimate) | 315 MB | Fits | not known | not known |