Text / zai-org

GLM 5.2

GLM-5.2 is an MIT-licensed text-generation model from zai-org, presented as a flagship model for long-horizon tasks with a 1M-token context. It is tagged with safetensors and text-generation, supports English and Chinese, and uses the transformers library. The card describes improved architecture, coding capabilities with multiple thinking effort levels, and local serving support via SGLang, vLLM, Transformers, and KTransformers, with a newer version GLM-5.3-BF16 noted.

EstimatedRepository opened Jun 16, 2026Source checked 9/24/2026Version: cf457fa7

LOCALRENTED GPUOPEN WEIGHTS

Freshness 63 out of 100. Repository age: 121 days old, Jun 16, 2026. Measures age, not quality.

Popularity 80 out of 100. 492,903 downloads in 30 days; 5,181 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

WORKFLOWS FOR THIS MODEL 1

What do you want to do?

Choose a task. Get the software, files, settings, and steps to run it.

MAKE IT PERSONALChoose your hardware

Coding

Build a coding assistant with GLM 5.2 on rented GPUs

Use a publisher GLM 5.2 checkpoint on a capable multi-GPU Linux host, connect VS Code/Cline privately from Windows or Mac, and verify a small code change.

Freshness 63 out of 100. Repository age: 121 days old, Jun 16, 2026. Measures age, not quality.

VS CodeCline

2 packagesLinux

Open coding guide

Open a guide for its software, hardware requirements, and setup steps.

At a glance

Parameters: 753.33B
Architecture: glm_moe_dsa
Context length: 1,048,576
License: mit
Disk space: 1403.2 GB
Software: SGLang, vLLM

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

Long-horizon text-generation tasks
Coding tasks with adjustable thinking effort levels
English and Chinese language generation
Local serving with supported frameworks such as SGLang, vLLM, Transformers, and KTransformers
Agentic and tool-use scenarios as suggested by benchmark names

Tradeoffs

Only limited facts are supplied; unspecified capabilities, parameters, and requirements are not inferred
Performance, compatibility, and numerical hardware requirements are not established
Local serving depends on externally specified framework versions
The model card references a newer version, GLM-5.3-BF16
No testing or purchase recommendation is made

Ways to run it

SGLang · Linux / rented GPU

Publisher-linked deployment recipe; follow the maintained runtime instructions at the source.

Official instructions

vLLM · Linux / rented GPU

Publisher-linked deployment recipe; follow the maintained runtime instructions at the source.

Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text

Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 90 out of 100. Release age: 28 days old, Sep 17, 2026. Measures age, not quality.

MODEL SIZE27.36B

LOCALRENTED GPU

Released Sep 17, 2026

Text

DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

Freshness 87 out of 100. Repository age: 35 days old, Sep 10, 2026. Measures age, not quality.

Arena Open Source Text: rank 5 of 225. Ranked model: deepseek-v4.1-flash-max. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3

LOCALRENTED GPU

Repository opened Sep 10, 2026

Text

Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats

LOCALRENTED GPU

Compare versions →