Gemma 3 27B IT

Release Date: Mar 12, 2025     Creator: Google

A high-performance open-weight model from Google, capable of efficient text and multimodal understanding.

Model Specifications
Knowledge Cutoff
Aug 31 2024
N/A
Context (VividLLM)
32,000 Tokens
N/A Tokens
With a context window of 32,000 tokens, this model can 'remember' and analyze up to 48 pages of data at once. This makes it a top choice for reviewing legal contracts and dense academic chapters.
Context (Native)
128,000 Tokens
N/A Tokens
Input ModalitiesTextImagePDFTextImagePDF
Output TypeTextText
Max Output81928192
Input Weight
0.40 x (Casual)
N/A
Output Weight
0.40 x (Casual)
N/A
Industry Benchmarks
Intelligence Index (Artificial Analysis) 10.3 N/A
Coding Index (Artificial Analysis)9.6N/A
Math Index (Artificial Analysis)20.7N/A
Response Speed
Output Tokens per second 36.23 N/A
Median Time to First Token Seconds0.66sN/A
Launch VividLLM Now => :

Benchmarks accessed via : Artificial Analysis

Disclaimer: We are providing Image Upload options to only limit models as of now, so some models which have image upload options might now have that feature on our site.