Google · open-weights model
gemma-2-2b-it
gemma-2-2b-it is a 2.6B-parameter model by Google. Its smallest quant (Q4_K_M) needs at least 2.6GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 50 of the 50 machines we track.
- Parameters
- 2.6B
- Layers
- 26
- Max context
- 8K
- Attention
- SLIDING-WINDOW
- License
- gemma
Config from google/gemma-2-2b-it
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 2.8 GB | 3.6 GB |
| Q6_K | 2.1 GB | 3.0 GB |
| Q5_K_M | 1.9 GB | 2.8 GB |
| Q4_K_M | 1.7 GB | 2.6 GB |
What runs gemma-2-2b-it
Every machine we track, graded at its best clean-fit quant.
Verdicts computed from published specs and measured GGUF sizes — how the math works.