Google: Gemma 4 26B A4B (free)
Released Apr 3, 2026Try it on:
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference - delivering near-31B quality at...
Best overall rank
-
Across all subsets · overall
Total arena votes
0
Across 0 (subset, category) entries
Providers on OR
0
None yet
First seen
-
Awaiting first snapshot
Trend
No snapshot history yet - trends appear after the first daily refresh.
Pricing
No priced fields.
Capabilities
Modality
text+image+video->textContext
262K tokens
Tokenizer
Gemma
Max output
33K tokens
Moderation
Unmoderated
Hugging Face
Supported parameters
include_reasoning
max_tokens
reasoning
response_format
seed
temperature
tool_choice
tools
top_p
Providers
No provider endpoint data yet.
Per-category ranks
No leaderboard entries for this model.