Gemma 2B
Gemma 2B is an open-weights language model from Google, released February 21, 2024. It has 2B parameters (dense). On the Epoch Capabilities Index it scores 76.0, rank 241 of 256 rated models.
Check it against your own PC →
Lab
Google
Released
February 21, 2024
Weights
Open restricted use
Parameters
2B dense
Context
–
Price / M tokens
–
Epoch ECI
76.0 #241
Can you run Gemma 2B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, fully on GPU, roughly 66 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 3.8 GB | – | ~66 |
| 8 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 3.8 GB | – | ~91 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 3.8 GB | – | ~120 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 3.8 GB | – | ~150 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 3.8 GB | – | ~260 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 3.8 GB | – | ~400 |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 23.1% |
Links
Models with a similar score
LLaMA-7B · DeepSeek Coder 33B · vicuna-13b-v1.1 · CodeQwen1.5-7B · chatglm2-6b · MPT-7B · Falcon-7B · StarCoder 2 7B
More from Google
Gemini 4 Carbon · Gemini 4 Argon · Gemini 3.8 Flash · Gemini 3.7 Flash · Gemini 3.6 Flash · Gemini 3.5 Flash-Lite · Gemini 3.5 Flash Cyber · Gemma 4 E4B