Can I run JiRackUltra_14b on an RTX 3060 12 GB?
Probably, at 4-bit
The published weights are too big, but a 4-bit version (about 8.31 GB) would fit, with room for ≈ 12K tokens of context. The site hasn't analyzed a GGUF of JiRackUltra_14b yet.
Files and context on RTX 3060 12 GB
Each file of JiRackUltra_14b (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 | 29.5 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 8.31 GB | Fits | 12K | 25K |