GLM-OCR vs Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Specs, VRAM requirements and download trends — updated 6 August 2026.

zai-org · A
Params
1.3 B
Context
30d
3.8 M
mit · commercial OK
HauhauCS · B
Params
Context
30d
1.9 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification GLM-OCR Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Parameters 1.3 B
Architecture GlmOcrForConditionalGeneration
Context length
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages 8 3
Downloads 30d 3,769,294 1,930,898
Downloads all time 28.1 M 8.9 M
Quantizations on the Hub SAFETENSORS GGUF
Gated No No
First seen on the Hub 2026-01-30 2026-04-17

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

3.8 M1.8 M
GLM-OCR Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

VRAM side by side

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

GLM-OCR · fp16 3.6 GB / 24 GB
✅ Runs comfortably
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive · Q4_K_M 23.8 GB / 24 GB
⚠️ Tight — reduce context

Adjacent comparisons