Gemma 4 26B-A4B
visionMoE
25,8B
Parameters · 4B active
15,9 Go
Q4_K_M file
≥ 17,4 Go
Recommended VRAM
262 144
Max context
Not measured yet
No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.
Measure my card →Which cards should it fit on?
Cards on the site whose video memory covers the recommended 17,4 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.
Technical sheet
- Published
- 2026-03-11
- Architecture
- 30 layers · 8 KV heads · dimension 256
- Attention
- Sliding window: 5 of 30 layers keep the whole context, the others only the last 1024 tokens — a much lighter cache.
- Context cache (f16)
- ≈ 39 MB per 1,000 tokens · 1,3 Go for 32,768 tokens
- GGUF file
- bartowski/google_gemma-4-26B-A4B-it-GGUF · google_gemma-4-26B-A4B-it-Q4_K_M.gguf Download (15,9 Go)
- Official repo
- google/gemma-4-26B-A4B-it
Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.