Gemma 4 26B A4B
Gemma 4 26B A4B is an open-weights language model from Google, released April 2, 2026. It has 26B parameters (mixture-of-experts, 4B active). The context window is 256K tokens. On the Epoch Capabilities Index it scores 141.6, rank 113 of 256 rated models.
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 26B A4B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, GPU + experts in RAM, roughly 13 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 · GPU + CPU experts | Q6_K (≈ lossless) | 5.2 GB | 19.4 GB | ~13 |
| 8 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 7.2 GB | 17.4 GB | ~15 |
| 12 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 11.2 GB | 13.4 GB | ~19 |
| 16 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 15.2 GB | 9.4 GB | ~25 |
| 24 GB VRAM | Runs on GPU | Q5_K_M (excellent) | 21.8 GB | – | ~160 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 24.6 GB | – | ~250 |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 82.2% |
| GPQA Diamond | 67.0% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Gemini 3.5 Flash-Lite · Kimi K2 Thinking · o4-mini · Gemini 3.1 Flash-Lite · Gemini 2.5 Pro (Jun 2025) · Claude Opus 4.1 · DeepSeek-V3.2-Exp · Grok 4 Fast
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