# GLM-Edge

GLM-Edge is an AI model released by Z.ai on Nov 29 2024. It has 1.5B/4B parameters, an 8k context window and open weight.

## Facts

| Field | Value |
| --- | --- |
| Model | GLM-Edge |
| Developer | Z.ai |
| Release date | Friday, Nov 29 2024 |
| Licensing | Open Weight |
| Parameters | 1.5B/4B |
| Context window | 8k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| MMLU | 54.84% | [PLM authors, Table 10](https://arxiv.org/html/2503.12167#S5.T10), retrieved 2026-11-18 | A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. |
| GSM8K | 54.89% | [PLM authors, Table 10](https://arxiv.org/html/2503.12167#S5.T10), retrieved 2026-11-18 | Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. |

## About GLM-Edge

Zhipu AI introduced the text models in GLM-Edge on November 29, 2024 as lightweight assistants for local devices. The 1.5B model targeted phones and vehicle systems, while the 4B model targeted personal computers.

The downloadable chat checkpoints both supported 8,192-token sequences and were available in quantized GGUF builds. The PLM authors independently evaluated the 1.5B model, measuring 54.84% on MMLU and 54.89% on GSM8K.

## Questions and answers

### When was GLM-Edge released?

GLM-Edge was released by Z.ai on Friday, Nov 29 2024.

### Who made GLM-Edge?

GLM-Edge was built by Z.ai. Chinese AI lab spun out of Tsinghua University (formerly Zhipu AI), building the open-weight GLM family. Rebranded internationally as Z.ai in 2025.

### What benchmark scores did GLM-Edge get?

GLM-Edge reports 2 tracked benchmark scores — MMLU: 54.84%; GSM8K: 54.89%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of GLM-Edge?

GLM-Edge has a context window of 8k. Providers may specify separate input and output token limits.

### How many parameters does GLM-Edge have?

GLM-Edge is reported at 1.5B/4B parameters.

### Is GLM-Edge open source?

Partly. GLM-Edge is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after GLM-Edge?

Z.ai's previous tracked release was GLM-4-Plus on Aug 29 2024, 92 days earlier. It was followed by GLM-4-0414 on Apr 14 2025.


---

Canonical page: https://aireleasetracker.com/model/zai/glm-edge
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
