Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

GLM 4 MoE-A10B

Model basics

Reasoning traces

Supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

4096 tokens

Model type

聊天大模型

Release date

2025-07-14

Model file size

200GB

MoE architecture

Yes

Total params / Active params

1000.0B / 100B

Knowledge cutoff

No data

GLM 4 MoE-A10B

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

GitHub link unavailable

Hugging Face

Hugging Face link unavailable

Live demo

No live demo

GLM 4 MoE-A10B

Official resources

Paper

No paper available

DataLearnerAI blog

No blog post yet

GLM 4 MoE-A10B

API details

API speed

3/5

No public API pricing yet.

GLM 4 MoE-A10B

Benchmark Results

No benchmark data to show.

GLM 4 MoE-A10B

Publisher

智谱AI

View publisher details

GLM4-MoE-100B-A10B

Model Overview

GLM4-MoE-100B-A10B是智谱AI开源的模型，不过截止2025年7月11日没有发布，但是在vLLM引擎的提交记录中，有人发现了这个模型的名字，应该是很快就会发布了~

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送