Can I run chandra-ocr-2 on an RTX 4060?
Probably, at 4-bit
The published weights are too big, but a 4-bit version (about 2.98 GB) would fit, with room for ≈ 124K tokens of context. The site hasn't analyzed a GGUF of chandra-ocr-2 yet.
Files and context on RTX 4060
Each file of chandra-ocr-2 (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 4060 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 10.6 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 2.98 GB | Fits | 124K | 249K |