Gemma 4 12B
Gemma 4 12B is an open-weights language model from Google, released June 3, 2026. It has 12B parameters (dense).
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
Check it against your own PC →
Can you run Gemma 4 12B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q4_K_M, split GPU / CPU, roughly 5 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, slowly | Q4_K_M (very good) | 5.2 GB | 5.2 GB | ~5 |
| 8 GB VRAM | Runs, slowly | Q5_K_M (excellent) | 7.2 GB | 4.4 GB | ~6 |
| 12 GB VRAM | Runs on GPU | Q4_K_M (very good) | 10.4 GB | – | ~29 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 12.9 GB | – | ~30 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 12.9 GB | – | ~54 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 12.9 GB | – | ~99 |
Benchmark results
Epoch AI has not published results for Gemma 4 12B yet. New models are usually evaluated within days to weeks.
Links
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