Written by Jakub Rusinowski · Last updated July 10, 2026
Google's fourth-generation open model family. The first wave (E2B, E4B, 26B-A4B MoE, 31B dense) launched March 31, 2026 under Apache 2.0 with a fully multimodal architecture — text, image, and audio across all sizes, plus video on the 31B. A separate 12B 'Unified' encoder-free model followed June 3, 2026, adding native audio+video to a laptop-friendly 16GB footprint. The E2B and E4B Efficient variants run on 4–6 GB VRAM GPUs, while the 26B-A4B MoE and 31B dense models deliver near-frontier quality on a single RTX 4090.
| Gemma 4 E2B | Min 4 GB VRAM · Q4 (QAT) · 128,000 ctx · ollama run gemma4:e2b |
| Gemma 4 E4B | Min 6 GB VRAM · Q4 (QAT) · 128,000 ctx · ollama run gemma4:e4b |
| Gemma 4 26B-A4B | Min 16 GB VRAM · Q4_K_M · 256,000 ctx · ollama run gemma4:26b-a4b |
| Gemma 4 31B | Min 20 GB VRAM · Q4_K_M · 256,000 ctx · ollama run gemma4:31b |
| Gemma 4 12B (Unified) | Min 8 GB VRAM · Q4_K_M · 128,000 ctx · ollama run gemma4:12b |
The cheapest GPU that runs Gemma 4 locally (min 4 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run gemma4:e2b
Minimum VRAM: 4 GB. For best results use Q4_K_M quantization.
Gemma 4 needs about 4 GB VRAM at Q4 (QAT) quantization for its smallest variant. Variants: Gemma 4 E2B (4 GB, Q4 (QAT)); Gemma 4 E4B (6 GB, Q4 (QAT)); Gemma 4 26B-A4B (16 GB, Q4_K_M); Gemma 4 31B (20 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Gemma 4 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4 (QAT).
Q4_K_M is the best balance of quality and VRAM for Gemma 4 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run gemma4:e2b. This downloads Gemma 4 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.