GLM-OCR vs Qwen3.6-35B-A3B-AWQ
Specs, VRAM requirements and download trends — updated 28 July 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-OCR | Qwen3.6-35B-A3B-AWQ |
|---|---|---|
| Parameters | 1.3 B | 36.0 B |
| Architecture | GlmOcrForConditionalGeneration | Qwen3_5MoeForConditionalGeneration |
| Context length | — | — |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 8 | — |
| Downloads 30d | 1,956,836 | 840,962 |
| Downloads all time | 30.7 M | 3.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-01-30 | 2026-04-17 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
3.8 M841 K
GLM-OCR
Qwen3.6-35B-A3B-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-OCR · fp16
3.6 GB / 24 GB
Qwen3.6-35B-A3B-AWQ · fp16
33.9 GB / 24 GB