DeepSeek-V3.2 vs GLM-5-NVFP4

Specs, VRAM requirements and download trends — updated 2 September 2026.

deepseek-ai · A
Params
685.4 B
Context
163,840
30d
2.5 M
mit · commercial OK
nvidia · B
Params
435.2 B
Context
202,752
30d
189 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification DeepSeek-V3.2 GLM-5-NVFP4
Parameters 685.4 B 435.2 B
Architecture DeepseekV32ForCausalLM GlmMoeDsaForCausalLM
Context length 163,840 202,752
Licence mit mit
Commercial use Allowed Allowed
Languages
Downloads 30d 2,488,767 188,640
Downloads all time 24.5 M 546 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-12-01 2026-02-24

Download trend

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

2.5 M159 K
DeepSeek-V3.2 GLM-5-NVFP4

VRAM side by side

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

GLM-5-NVFP4 · fp16 @ 198K ctx 2,145.2 GB / 24 GB
❌ Won’t fit
DeepSeek-V3.2 · fp16 @ 160K ctx 2,815.1 GB / 24 GB
❌ Won’t fit

Adjacent comparisons