Skip to content
OSMEXO

Gemma 3 12B IT

google/gemma-3-12b-it
  • Google
  • Family · Gemma 3
  • Open weights
  • Text · Image → Text
  • Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context128K
Max output16K
Input / 1M$0.05
Output / 1M$0.153× input
Usage
Tokens / day1.5B▼ 17% 7d
Usage rank#169
Requests / day1.1M
Tool calls / req0.00
Per request · 30 days
Avg input6850.0× median
Avg output670.1× median
Cache hit5.9%0.1× median
Tool-call failures4%2.1× median

Consumption

1.0B2.0B3.0B2 Oct16 Oct31 Oct
Peak 2.9B 16 OctLow 902.1M 31 OctRank today #169

News & trends

2 mentions this weekGemma 3 family · videos, posts, articles · 30 days
News · latest from Google

Benchmarks

Benchmark data: Artificial Analysis
Output speed#299/33328 tok/s2.4× slower than median
Fastest provider58 tok/sbest of 4 providers
First token#1641.02 sabout median
Family progress
Intelligence Index
3.544.555.5AprMayJunJulAug
  • Family releases5.1

Technical details

Tokenizer
Gemini
Knowledge cutoff
2024-08-31
License
gemma
Parameters
12.2B
Moderation
none
Downloads · likes
355.7K · 899
Request parameters 15
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • temperature
  • top_p
  • top_k
  • min_p
  • max_tokens
  • stop
+5 more
  • seed
  • frequency_penalty
  • logit_bias
  • presence_penalty
  • repetition_penalty

When to use

Best for

  • Self-hosted multimodal assistants
  • Image understanding with an open model
  • Document Q&A over long inputs
  • Tool-calling in lightweight agents
  • Low-cost classification and extraction

Think twice for

  • Hardest reasoning and coding tasks
  • Image or audio generation
  • Frontier-quality agent runs

Research papers

Same family

Gemma 3

Want Gemma 3 12B IT on OSMEXO?

Sign in to request it. Requests are reviewed; a request does not guarantee availability.