PyyanThe AI Index

Pyyan / Compare / Gemma 3 4B vs MiMo-V2.6-Flash

Gemma 3 4B vs MiMo-V2.6-Flash

2 of 5

Open-Weight Models · verified 29 Sept 2026

Gemma 3 4BGooglecurrent
XMiMo-V2.6-FlashXiaomicurrent
3 slots left
SpecificationGemma 3 4BMiMo-V2.6-Flash
SummaryMultimodal and 140+ languages at 4B.The small one, and still multimodal.
Context—1M
Input ($/Mtok)—Weights only
Output ($/Mtok)—Weights only
LicenceGemma licenceMIT
Max output—Not published
Parameters4B309B total, 15B active
Released—21 Sep 2026
Model ID—XiaomiMiMo/MiMo-V2.6-Flash
CategoryOpen-Weight ModelsOpen-Weight Models
OfficialGoogle ↗Xiaomi ↗

Highlighted rows are where these differ.

Gemma 3 4B

Multimodal and 140+ languages at 4B.

Best for multilingual edge.

Full spec sheet →

MiMo-V2.6-Flash

  • 309B total parameters, 15B active per token
  • Same 1M context and five layer speculative decoder as Pro
  • MIT licence, weights on Hugging Face

Best for multimodal work on your own cluster.

Full spec sheet →