LLM EXPLORER 68,292 MODELS INDEXED

Qwen3.8 27B Ocr Whole Page V2 R4 Bf16 by shbaydadaev

By shbaydadaev · 16 downloads

Qwen3.8 27B Ocr Whole Page V2 R4 Bf16 is an open-source language model by shbaydadaev. Features: 27b LLM, VRAM: 55GB, License: apache-2.0.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.8-27b   Chg   Conversational   Endpoints compatible   Fa   Image-text-to-text   Manuscript   Ocr   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Whole-page-transcription

Qwen3.8 27B Ocr Whole Page V2 R4 Bf16 Parameters and Internals

LLM NameQwen3.8 27B Ocr Whole Page V2 R4 Bf16
Repository πŸ€—https://huggingface.co/shbaydadaev/Qwen3.8-27B-ocr-whole-page-v2-r4-bf16 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM55 GB
Updated2026-11-22
Maintainershbaydadaev
Model Typeqwen3_5
Model Files  3.9 GB: 1-of-14   4.0 GB: 2-of-14   4.0 GB: 3-of-14   4.0 GB: 4-of-14   3.9 GB: 5-of-14   4.0 GB: 6-of-14   4.0 GB: 7-of-14   4.0 GB: 8-of-14   4.0 GB: 9-of-14   3.9 GB: 10-of-14   4.0 GB: 11-of-14   4.0 GB: 12-of-14   4.0 GB: 13-of-14   3.3 GB: 14-of-14
Supported Languagesfa
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.20.2
Tokenizer ClassQwen3_5Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B Ocr Whole Page V2 R4 Bf16

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB863
... 27B 6.3bpw RCO SAR Marlin MTP256K / 22 GB841
Qwen3.8 27B NPU2256K /  GB2524
...toTrust Decider Pro Vision 27B0K / 55.6 GB15373904526
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB220432237
Qwen3.6 27B0K / 55.4 GB67281382197
Arete 27B0K / 54.7 GB2407346
DaisyRose 27B0K / 55.6 GB166170
Note: green Score (e.g. "73.2") means that the model is better than shbaydadaev/Qwen3.8-27B-ocr-whole-page-v2-r4-bf16.