LLM EXPLORER 55,709 MODELS INDEXED

OlmOCR 7B 0225 Preview 4bit by mlx-community

By mlx-community · 22 downloads
HF Repo ↗ Copy URL

OlmOCR 7B 0225 Preview 4bit is an open-source language model by mlx-community. Features: 7b LLM, VRAM: 5.6GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based.

  4bit Base model:finetune:qwen/qwen2... Base model:qwen/qwen2-vl-7b-in...   Conversational Dataset:allenai/olmocr-mix-022...   En   Endpoints compatible   Image-text-to-text   Instruct   Mlx   Quantized   Qwen2 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/olmOCR-7B-0225-preview-4bit 

OlmOCR 7B 0225 Preview 4bit Parameters and Internals

LLM NameOlmOCR 7B 0225 Preview 4bit
Repository 🤗https://huggingface.co/mlx-community/olmOCR-7B-0225-preview-4bit 
Base Model(s)  Qwen2 VL 7B Instruct   Qwen/Qwen2-VL-7B-Instruct
Model Size7b
Required VRAM5.6 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen2_vl
Instruction-BasedYes
Model Files  5.3 GB: 1-of-2   0.3 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2VLForConditionalGeneration
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.49.0
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to OlmOCR 7B 0225 Preview 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 VL 7B Instruct 4bit32K / 4.7 GB6482
...L 7B Instruct Abliterated 8bit32K / 8.9 GB291
Qwen2 VL 7B Instruct 8bit32K / 8.9 GB362
Qwen2 VL 7B Instruct32K / 16.7 GB3337
Qwen2 VL 7B Instruct AWQ32K / 6.9 GB1075222
Qwen2 VL 7B Instruct GPTQ Int432K / 7 GB258814
Qwen2 VL 7B Instruct GPTQ Int832K / 10.2 GB126631
Qwen2 VL 7B Instruct Bf1632K / 16.6 GB504
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/olmOCR-7B-0225-preview-4bit.