Mellum2 12B
Built by JetBrains, for code
Install with Bobbin
Don't have the app? Download it here.
A coding model from the company behind IntelliJ and PyCharm, trained specifically for code completion and review.
It only uses part of itself for each word it writes, so it runs faster than its size suggests.
Available versions
| Quantization | Size | VRAM | RAM | Context | |
|---|---|---|---|---|---|
| Q4_K_M | 8.1 GB | 8.2 GBest. | 13.2 GB | 8k | Install |
Memory needed grows with the length of a conversation, so these figures are for the context shown. Anything marked est. is worked out from the file size rather than measured on real hardware — the app says so there too. The desktop app checks all of it against your actual machine before installing.