GLM 5.2 is live! Opus-level intelligence at open-source rates. Pay per token on serverless. Try it today.

Model Library/Z.ai/GLM 5.2 FP8
z.ai

GLM 5.2 FP8

Ready
Deploy on Demand
model path:accounts/fireworks/models/glm-5p2-fp8

GLM-5.2 FP8 checkpoint from zai-org/GLM-5.2-FP8

GLM 5.2 FP8 API Features

On-demand Deployment

Docs

On-demand deployments allow you to use GLM 5.2 FP8 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
6/18/2026
Kind
Base model
Provider
Z.ai
Hugging Face
zai-org/GLM-5.2-FP8

Specification

Calibrated
No
Mixture-of-Experts
Yes
Parameters
743B

Supported Functionality

Fine-tuning
Not supported
Serverless
Not supported
Context Length
1040k tokens
Function Calling
Supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported