surya-ocr-2 vs Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
Specs, VRAM requirements and download trends — updated 21 September 2026.
HauhauCS · B
Params
—
Context
—
30d
2.2 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | surya-ocr-2 | Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF |
|---|---|---|
| Parameters | 690 M | — |
| Architecture | Qwen3_5ForConditionalGeneration | — |
| Context length | — | — |
| Licence | openrail | apache-2.0 |
| Commercial use | Conditional | Allowed |
| Languages | — | 3 |
| Downloads 30d | 1,197,682 | 2,192,290 |
| Downloads all time | 3.6 M | 2.7 M |
| Quantizations on the Hub | SAFETENSORS | GGUF |
| Gated | No | No |
| First seen on the Hub | 2026-05-14 | 2026-08-17 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
2.4 M873 K
surya-ocr-2
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
surya-ocr-2 · fp16
2.1 GB / 24 GB
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF · Q4_K_P
20.2 GB / 24 GB
Adjacent comparisons
Qwen3-VL-8B-Instruct vs Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
gemma-4-26B-A4B-it vs Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
Qwen3.6-35B-A3B-FP8 vs Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
Qwen3.5-9B vs Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
gemma-4-31B-it vs Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
Qwen3.8-27B vs Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF