GLM 5 Models — Hardware Requirements

4 GLM 5 models from Z.ai and the community, from the smallest that runs in 211.4 GB of VRAM up to 753.9B parameters. Every row links to full quantization tables and GPU compatibility.

All GLM 5 Models by Size

ModelParamsContext
GLM 5.2 Speculator.dspark3.8B
GLM 5.2 W4AFP8391.9B1049K
GLM 5.2753.3B1049K
GLM 5753.9B203K
GLM 5.1753.9B203K
GLM 5 Abliterated753.9B203K

How GLM 5 Compares — Benchmark Rating

GLM 5.2 is the highest-rated GLM 5 model with an overall benchmark rating of 82.7/100 — #1 among 73 open models. The top proprietary model, Claude Fable 5 Max, scores 89.9. Click a model to see its full benchmark breakdown.

Claude Fable 5 Max · proprietary89.9
GPT 5.5 · proprietary89.2
GPT 5.6 Sol · proprietary89.2
Claude Fable 5 · proprietary88.6
Claude Opus 4.8 · proprietary88.1
GLM 563.6
Composite of normalized public benchmark scores (methodology) · GLM 5 · other models

Frequently Asked Questions

How much VRAM do I need to run a GLM 5 model?
The smallest GLM 5 model, GLM 5.2 Speculator.dspark, runs from 1.8 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which GLM 5 models can I run on a 16 GB GPU?
1 of 6 GLM 5 models fit in 16 GB of VRAM at some quantization, including GLM 5.2 Speculator.dspark.
What is the most popular GLM 5 model to run locally?
GLM 5.2 is the most downloaded GLM 5 model in local-friendly quantized formats. It runs from 211.4 GB of VRAM.
How do GLM 5 models score on benchmarks?
GLM 5.2 leads the family with an overall benchmark rating of 82.7/100, ranking #1 among 73 open models, while the top proprietary model, Claude Fable 5 Max, scores 89.9. See the comparison chart above for the full standings.
GLM 5 Models — VRAM & Hardware Requirements | llmrun