What are the hardware requirements for Dolphin 2.8 Mistral 7B V02?

Dolphin 2.8 Mistral 7B V02 requires approximately 14.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dolphin 2.8 Mistral 7B V02 and how large is it?

Dolphin 2.8 Mistral 7B V02 is developed by cognitivecomputations, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Dolphin 2.8 Mistral 7B V02 perform on standard benchmarks?

Dolphin 2.8 Mistral 7B V02 has the following published scores: MMLU 62.59. Compare against reference models on this page or on the LLM Explorer leaderboards.

Dolphin 2.8 Mistral 7B V02 by cognitivecomputations — VRAM 14.4GB, 32K context

Name: Dolphin 2.8 Mistral 7B V02
Author: cognitivecomputations

Dolphin 2.8 Mistral 7B V02 is an open-source language model by cognitivecomputations. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Instruction-Based, HF Score: 63.6, LLM Explorer Score: 0.16, Arc: 62.7, HellaSwag: 83.8, MMLU: 62.6, TruthfulQA: 49.6, WinoGrande: 79.3, GSM8K: 43.8.

Autotrain compatible Base model:finetune:mistral-co... Base model:mistral-community/m... Conversational Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:jondurbin/airoboros-2.... Dataset:m-a-p/code-feedback Dataset:m-a-p/codefeedback-fil... Dataset:teknium/openhermes-2.5 En Endpoints compatible Instruct Mistral Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02

Dolphin 2.8 Mistral 7B V02 Benchmarks

ARC: 62.71 vs 96.7 (so35)^-35.1%

HellaSwag: 83.8 vs 95.3 (gpt4)^-12.1%

MMLU: 62.59 vs 88.3 (so35)^-29.1%

TruthfulQA: 49.58 vs 59 (gpt4)^-16%

WinoGrande: 79.32 vs 87.5 (gpt4)^-9.3%

GSM8K: 43.75 vs 96.4 (so35)^-54.6%

LLME Score: 0.15875

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Dolphin 2.8 Mistral 7B V02 (cognitivecomputations/dolphin-2.8-mistral-7b-v02)

🌟 Advertise your project 🚀

Dolphin 2.8 Mistral 7B V02 Parameters and Internals

Model Type

text-generation

Additional Notes

Model recommended to have an alignment layer to ensure ethical use.

Supported Languages

en (high)

Training Details

Data Sources:

/workspace/datasets/dolphin201-sharegpt2.jsonl, /workspace/datasets/dolphin-coder-translate-sharegpt2.jsonl, /workspace/datasets/dolphin-coder-codegen-sharegpt2.jsonl, /workspace/datasets/m-a-p_Code-Feedback-sharegpt.jsonl, /workspace/datasets/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt.jsonl, /workspace/datasets/not_samantha_norefusals.jsonl, /workspace/datasets/openhermes2_5-sharegpt.jsonl

Methodology:

fine-tuning

Context Length:

16384

Training Time:

3 days

Hardware Used:

10x L40S from Crusoe Cloud

Model Architecture:

MistralForCausalLM

Input Output

Accepted Modalities:

text

LLM Name	Dolphin 2.8 Mistral 7B V02
Repository 🤗	https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02
Base Model(s)	alpindale/Mistral-7B-v0.2-hf alpindale/Mistral-7B-v0.2-hf
Model Size	7b
Required VRAM	14.4 GB
Updated	2025-07-13
Maintainer	cognitivecomputations
Model Type	mistral
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32002
Torch Data Type	bfloat16

Quantized Models of the Dolphin 2.8 Mistral 7B V02

Model	Likes	Downloads	VRAM
Dolphin 2.8 Mistral 7B V02 AWQ	2	14	4 GB

Best Alternatives to Dolphin 2.8 Mistral 7B V02

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	254	20
SpydazWeb AI HumanAI RP	512K / 14.4 GB	21	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
... Summarize 64K QLoRANET Merged	128K / 4.1 GB	6	0
...1 Summarize 64K LoRANET Merged	128K / 14.4 GB	6	0
Mistral 7B Instruct V0.2	32K / 14.4 GB	3316095	2630
Mistral 7B Instruct V0.1	32K / 14.4 GB	416943	1832
Mistral 7B Instruct V0.2	32K / 14.4 GB	5759	0
Ghost V5 Ultra 8B	32K / 14.5 GB	99	0

Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-2.8-mistral-7b-v02.

Rank the Dolphin 2.8 Mistral 7B V02 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53254 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Dolphin 2.8 Mistral 7B V02 by cognitivecomputations