Gemma 4 E2B
Gemma 4 E2B is an open-weights language model from Google, released July 2, 2026. It has 5.1B parameters (dense). The context window is 128K tokens.
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters.
Check it against your own PC →
Can you run Gemma 4 E2B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, fully on GPU, roughly 27 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) | 4.9 GB | – | ~27 |
| 8 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.9 GB | – | ~37 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.9 GB | – | ~49 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.9 GB | – | ~67 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.9 GB | – | ~120 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.9 GB | – | ~200 |
Ready-made quantizations on Hugging Face: YoSaNoo/Forge-1-Gemma-4-E2B · mradermacher/gemma-4-E2B-i1-GGUF · mradermacher/gemma-4-E2B-GGUF · ggml-org/gemma-4-E2B-GGUF · Mungert/gemma-4-E2B-it-GGUF · Jessylg27/gemma-4-E2B-GGUF
Benchmark results
Epoch AI has not published results for Gemma 4 E2B yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: google/gemma-4-E2B
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