Google
Gemma 2 27B (27B parameters) requires approximately 29.5 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 34 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Gemma 2 27B on your machine.
Run
ollama run gemma2:27bQuick specs
About this model
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 10.5 GB | Low | — |
Q3_K_S | 3 | 13.2 GB | Low | — |
NVFP4 | 4 | 15.1 GB | Medium | — |
Q4_K_M | 4 | 16.5 GB | Medium | — |
Q5_K_M | 5 | 19.4 GB | High | — |
Q6_K | 6 | 22.1 GB | High | — |
Q8_0 | 8 | 28.9 GB | Very High | — |
F16 | 16 | 55.4 GB | Maximum | — |
Quality benchmarks
Coding
Reasoning
General
Source: official · 2024-06-27
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
Gemma 2 27B (27B parameters) requires approximately 29.5 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Mac mini M4 64GB can run Gemma 2 27B with a compatibility score of 68/100. It provides 64 GB of memory and achieves approximately 6.9 tokens per second.
The recommended quantization for Gemma 2 27B is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for Gemma 2 27B: RTX PRO 5000 Blackwell 48GB (score: 76/100), NVIDIA A100 40GB (score: 75/100), RTX 6000 Ada 48GB (score: 75/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, Gemma 2 27B is well-suited for chat as well as reasoning. It was designed with these use cases in mind.
See also
