Text model · gemma
Gemma 2 27B requirements
gemma family · 27B params · released Jun 2024 · 17.2M Ollama pulls · LMArena Elo 1289. Minimum to run at Q4_K_M: Nvidia GeForce RTX 4090 (24GB).
Quantization sizes
| Quantization | Size on disk |
|---|---|
| Q2_K | 11.3 GB est |
| Q3_K_M | 13.2 GB est |
| Q4_K_M (default) | 16.65 GB |
| Q5_K_M | 19.2 GB est |
| Q6_K | 22.1 GB est |
| Q8_0 | 28.94 GB |
| FP16 | 54 GB est |
Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.
Run it
ollama run gemma2:27b llama-cli -hf bartowski/gemma-2-27b-it-GGUF:Q4_K_M lms get bartowski/gemma-2-27b-it-GGUF Which devices can run Gemma 2 27B?
Apple Silicon Macs
RAM-only laptops
iPhone & iPad
Android
NVIDIA GPUs
AMD GPUs
FAQ
How much VRAM or RAM does Gemma 2 27B need?
At Q4_K_M, Gemma 2 27B needs about 18.7 GB (weights ~16.65 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~30.9 GB.
Can Gemma 2 27B run on a laptop?
Gemma 2 27B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.
Can I use Gemma 2 27B commercially?
Conditionally. Gemma Terms of Use apply to commercial use.
Released June 27, 2024. Uses sliding window attention with 8K context. Ollama default tag shows 16GB; bartowski HF repo gives precise 16.65GB Q4_K_M and 28.94GB Q8_0.
Sources
Memory figures are estimates. See methodology.