GLM 5.2 Fast is available! Opus-level intelligence at open-source rates. No contracts, pay per token. Start building.

Model Library/Fireworks AI/BGE-M3
Fireworks Logo Mark

BGE-M3

Ready
Deploy on Demand
model path:accounts/fireworks/models/bge-m3

BAAI bge-m3 multilingual embedding model (XLM-RoBERTa-large, 1024-dim dense, 8192 ctx).

BGE-M3 API Features

On-demand Deployment

Docs

On-demand deployments allow you to use BGE-M3 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
6/29/2026
Kind
Embedding model
Provider
Fireworks AI
Hugging Face
BAAI/bge-m3

Specification

Calibrated
No
Mixture-of-Experts
No
Parameters
567M

Supported Functionality

Fine-tuning
Not supported
Serverless
Not supported
Context Length
8.19k tokens
Function Calling
Not supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported