Can I run Clover-35B-A3B-Preview on an RTX 3060 12 GB?
No
Even its smallest file (4-bit (estimate), 19.5 GB) is more than an RTX 3060 12 GB can hold (10.8 GB usable): it needs 2 of them.
Files and context on RTX 3060 12 GB
Each file of Clover-35B-A3B-Preview (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 | 69.3 GB | Doesn't fit | — | — |
| Q8_0 | 37.9 GB | Doesn't fit | — | — |
| Q4_K_M | 23.0 GB | Doesn't fit | — | — |
| Q4_0 | 19.6 GB | Doesn't fit | — | — |