Gemma 4 31B
Google's flagship open model
Install with Bobbin
Don't have the app? Download it here.
The largest Gemma, under a permissive licence. Excellent written output and strong on following detailed instructions.
A direct alternative to Qwen3.8 27B — worth trying both and keeping whichever suits your work.
Available versions
| Quantization | Size | VRAM | RAM | Context | |
|---|---|---|---|---|---|
| Q4_K_M | 18.3 GB | 17.7 GBest. | 27.3 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.