Unlimited-OCR vs Qwen3.8-27B-MLX-4bit
Specs, VRAM requirements and download trends — updated 10 November 2026.
lmstudio-community · B · Open weights
Params
4.7 B
Context
—
30d
3.0 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Unlimited-OCR | Qwen3.8-27B-MLX-4bit |
|---|---|---|
| Parameters | 3.3 B | 4.7 B |
| Architecture | UnlimitedOCRForCausalLM | Qwen3_5ForConditionalGeneration |
| Context length | 32,768 | — |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 5,404,539 | 3,048,666 |
| Downloads all time | 14.2 M | 11.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-06-19 | 2026-08-14 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
5.4 M890 K
Unlimited-OCR
Qwen3.8-27B-MLX-4bit
A overtook B on 30 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Unlimited-OCR · fp16
15.7 GB / 24 GB
Qwen3.8-27B-MLX-4bit · fp16
18.9 GB / 24 GB