What are the hardware requirements for OlmOCR 2 7B 1025 Bf16?

OlmOCR 2 7B 1025 Bf16 requires approximately 16.6 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OlmOCR 2 7B 1025 Bf16 and how large is it?

OlmOCR 2 7B 1025 Bf16 is developed by mlx-community, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate OlmOCR 2 7B 1025 Bf16?

OlmOCR 2 7B 1025 Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OlmOCR 2 7B 1025 Bf16 by mlx-community — VRAM 16.6GB, 125K context

Name: OlmOCR 2 7B 1025 Bf16
Author: mlx-community

OlmOCR 2 7B 1025 Bf16 is an open-source language model by mlx-community. Features: 7b LLM, VRAM: 16.6GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-7b-... Conversational En Endpoints compatible Image-text-to-text Instruct Mlx Qwen2 5 vl Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/olmOCR-2-7B-1025-bf16

OlmOCR 2 7B 1025 Bf16 Parameters and Internals

LLM Name	OlmOCR 2 7B 1025 Bf16
Repository 🤗	https://huggingface.co/mlx-community/olmOCR-2-7B-1025-bf16
Base Model(s)	Qwen/Qwen2.5-VL-7B-Instruct Qwen/Qwen2.5-VL-7B-Instruct
Model Size	7b
Required VRAM	16.6 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen2_5_vl
Instruction-Based	Yes
Model Files	5.3 GB: 1-of-4 5.3 GB: 2-of-4 4.9 GB: 3-of-4 1.1 GB: 4-of-4
Supported Languages	en
Model Architecture	Qwen2_5_VLForConditionalGeneration
License	apache-2.0
Context Length	128000
Model Max Length	128000
Transformers Version	4.57.0
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Errors	replace

Rank the OlmOCR 2 7B 1025 Bf16 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to OlmOCR 2 7B 1025 Bf16

Best Alternatives	Context / RAM	Downloads	Likes
OmniLong Qwen2.5 VL 7B	512K / 16.6 GB	7	2
Qwen2.5 VL 7B Instruct FP4	125K / 7.2 GB	49165	3
Qwen2.5 VL 7B Instruct NVFP4	125K / 7.2 GB	8092	16
ZwZ 7B	125K / 16.6 GB	32	10
Qwen2.5 VL 7B Instruct FP8	125K / 10 GB	1009	8
ScaleCUA 7B	125K / 16.6 GB	115	11
HuatuoGPT Vision 7B Qwen2.5VL	125K / 16.6 GB	358	11
ViLaSR	125K / 16.7 GB	38	18
Holo1 7B Bf16	125K / 16.6 GB	24	2
Qwen2.5 VL 7B Instruct Bf16	125K / 16.6 GB	160	3

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/olmOCR-2-7B-1025-bf16.