GLM-5-FP8 vs GLM-5.2

Specs, VRAM requirements and download trends — updated 17 September 2026.

zai-org · A
Params
753.9 B
Context
202,752
30d
203 K
mit · commercial OK
zai-org · B
Params
753.3 B
Context
1,048,576
30d
962 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification GLM-5-FP8 GLM-5.2
Parameters 753.9 B 753.3 B
Architecture GlmMoeDsaForCausalLM GlmMoeDsaForCausalLM
Context length 202,752 1,048,576
Licence mit mit
Commercial use Allowed Allowed
Languages 2 2
Downloads 30d 202,976 961,717
Downloads all time 13.0 M 4.4 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-02-11 2026-06-16

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

2.8 M203 K
GLM-5-FP8 GLM-5.2

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

GLM-5-FP8 · fp16 @ 198K ctx 3,631.2 GB / 24 GB
❌ Won’t fit
GLM-5.2 · fp16 @ 1024K ctx 16,121.8 GB / 24 GB
❌ Won’t fit

Adjacent comparisons