runlocal.devCheck My GPU →

GLM 5.1

GLM

#1 open-source model on Code Arena. Exceptional for software development, within 3 points of Claude Opus on agentic benchmarks.

Provider

Zhipu AI

Parameters

~32B

Context

128K

Released

2026-04-08

VRAM Requirements by Quantization

MethodDisk SizeVRAM RequiredFits GPUs
Q8_032.5 GB35 GB1 GPUs
Q4_K_M18 GB20 GB7 GPUs
Q4_017.2 GB19 GB7 GPUs

Install with Ollama

Run in terminal:

ollama pull glm-5.1

Minimum 19GB VRAM required. Install Ollama from ollama.com

Benchmark Scores

mmlu87.2%
humaneval91.5%

Scores are approximate and may vary by quantization level.

Compatible GPUs (7)

HuggingFace

zai-org/GLM-5.1

View on HF →