Google · open-weights model
gemma-3-27b-it
gemma-3-27b-it is a 27.4B-parameter model by Google. Its smallest quant (Q4_K_M) needs at least 21.2GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 16 of the 50 machines we track.
- Parameters
- 27.4B
- Layers
- 62
- Max context
- 128K
- Attention
- HYBRID
- License
- gemma
Config from google/gemma-3-27b-it
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 28.7 GB | 33.4 GB |
| Q6_K | 22.2 GB | 26.9 GB |
| Q5_K_M | 19.3 GB | 24.0 GB |
| Q4_K_M | 16.6 GB | 21.2 GB |
What runs gemma-3-27b-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.