What are the hardware requirements for Dolphin Vision 7B?

Dolphin Vision 7B requires approximately 16.1 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dolphin Vision 7B and how large is it?

Dolphin Vision 7B is developed by cognitivecomputations, a model with 72b 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 Dolphin Vision 7B?

Dolphin Vision 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dolphin Vision 7B by cognitivecomputations — VRAM 16.1GB, 128K context

Name: Dolphin Vision 7B
Rating: 2 (1 reviews)
Author: cognitivecomputations

Dolphin Vision 7B is an open-source language model by cognitivecomputations. Features: 72b LLM, VRAM: 16.1GB, Context: 128K, License: other, LLM Explorer Score: 0.14.

Autotrain compatible Axolotl Base model:finetune:qwen/qwen2... Base model:qwen/qwen2-72b Bunny-qwen Conversational Custom code Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:internlm/agent-flan Dataset:locutusque/function-ca... Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-math-wo... Dataset:teknium/openhermes-2.5 Endpoints compatible Generated from trainer Region:us Safetensors Sharded Tensorflow Vision

Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-vision-7b

Dolphin Vision 7B Parameters and Internals

Model Type

multimodal

Additional Notes

DolphinVision is capable of reasoning and commenting on images that other popular models might object to.

Training Details

Data Sources:

cognitivecomputations/Dolphin-2.9, teknium/OpenHermes-2.5, m-a-p/CodeFeedback-Filtered-Instruction, cognitivecomputations/dolphin-coder, cognitivecomputations/samantha-data, microsoft/orca-math-word-problems-200k, Locutusque/function-calling-chatml, internlm/Agent-FLAN

Hardware Used:

8x mi300x node provided by TensorWave

LLM Name	Dolphin Vision 7B
Repository 🤗	https://huggingface.co/cognitivecomputations/dolphin-vision-7b
Base Model(s)	Qwen2 72B Qwen/Qwen2-72B
Model Size	72b
Required VRAM	16.1 GB
Updated	2025-07-13
Maintainer	cognitivecomputations
Model Type	bunny-qwen
Model Files	4.9 GB: 1-of-4 4.9 GB: 2-of-4 5.0 GB: 3-of-4 1.3 GB: 4-of-4 0.0 GB
Model Architecture	BunnyQwenForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.41.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Dolphin Vision 7B 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 Dolphin Vision 7B

Best Alternatives	Context / RAM	Downloads	Likes
Dolphin Vision 7B	128K / 16.1 GB	24539	57
Dolphin Vision 72B	128K / 147 GB	319	129
Dolphin Vision 72B	128K / 147 GB	31	134
Dolphin Vision 72B 4bit	128K / 41.2 GB	1038	7

Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-vision-7b.