Qwen3.5-4B vs GLM-OCR
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.5-4B | GLM-OCR |
|---|---|---|
| Parameters | 4.7 B | 1.3 B |
| Architecture | Qwen3_5ForConditionalGeneration | GlmOcrForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | 8 |
| Downloads 30d | 6,725,631 | 3,769,294 |
| Downloads all time | 34.1 M | 28.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-27 | 2026-01-30 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
6.7 M3.6 M
Qwen3.5-4B
GLM-OCR
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-OCR · fp16
3.6 GB / 24 GB
Qwen3.5-4B · fp16
11.5 GB / 24 GB