Google · 27B (4B active) · Mixture of Experts
Gemma 4 MoE instruct model (official) Check if your GPU or Mac can run Gemma 4 26B-A4B IT locally — 15.1 GB min, 25.1 GB recommended.
2026-04256K context
Mixture of Experts
Total experts: 26
Active experts: 4
Active params: 4.0B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q4_K_M | 4 | 14.3 GB | good | — |
| Q6_K | 6 | 21.2 GB | excellent | — |
| Q8_0 | 8 | 28.2 GB | excellent | — |
Can I run Gemma 4 26B-A4B IT locally?
- Can I run Gemma 4 26B-A4B IT locally?
- Gemma 4 26B-A4B IT needs about 15.1 GB of memory at a minimum and 25.1 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Gemma 4 26B-A4B IT need?
- At Q4_K_M, Gemma 4 26B-A4B IT uses about 14.3 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.