Kimi K3 on Fireworks: Frontier Intelligence You Can Own

Model Library/Google/Gemma 3 27B Instruct
Google Ai Logo Mark

Gemma 3 27B Instruct

Ready
Deploy on Demand
Fine-tune
model path:accounts/fireworks/models/gemma-3-27b-it

Gemma 3 27B Instruct

Gemma 3 27B Instruct API Features

Fine-tuning

Docs

Gemma 3 27B Instruct can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

On-demand Deployment

Docs

On-demand deployments allow you to use Gemma 3 27B Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Gemma 3 27B Instruct FAQs

Metadata

State
Ready
Created on
4/15/2025
Kind
Base model
Provider
Google
Hugging Face
google/gemma-3-27b-it

Specification

Calibrated
No
Mixture-of-Experts
No
Parameters
28.4B

Supported Functionality

Fine-tuning
Supported
Serverless
Not supported
Context Length
131k tokens
Function Calling
Not supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported