GLM-5.2-FP8 vs DeepSeek-V4-Pro

Specs, VRAM requirements and download trends — updated 21 September 2026.

zai-org · A
Params
753.3 B
Context
1,048,576
30d
978 K
mit · commercial OK
deepseek-ai · B
Params
1,598.8 B
Context
1,048,576
30d
569 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification GLM-5.2-FP8 DeepSeek-V4-Pro
Parameters 753.3 B 1,598.8 B
Architecture GlmMoeDsaForCausalLM DeepseekV4ForCausalLM
Context length 1,048,576 1,048,576
Licence mit mit
Commercial use Allowed Allowed
Languages 2
Downloads 30d 977,752 569,497
Downloads all time 6.4 M 10.6 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-06-16 2026-04-22

Download trend

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

3.1 M569 K
GLM-5.2-FP8 DeepSeek-V4-Pro

VRAM side by side

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

GLM-5.2-FP8 · fp16 @ 1024K ctx 15,295.6 GB / 24 GB
❌ Won’t fit
DeepSeek-V4-Pro · fp16 @ 1024K ctx 31,649.4 GB / 24 GB
❌ Won’t fit

Adjacent comparisons