What are the hardware requirements for Airoboros 65B Gpt4 M2.0?

Airoboros 65B Gpt4 M2.0 requires approximately 130.4 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Airoboros 65B Gpt4 M2.0 and how large is it?

Airoboros 65B Gpt4 M2.0 is developed by jondurbin, a model with 65b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Airoboros 65B Gpt4 M2.0 perform on standard benchmarks?

Airoboros 65B Gpt4 M2.0 has the following published scores: MMLU 64.32. Compare against reference models on this page or on the LLM Explorer leaderboards.

Airoboros 65B Gpt4 M2.0 by jondurbin — VRAM 130.4GB, 2K context

Name: Airoboros 65B Gpt4 M2.0
Author: jondurbin

Airoboros 65B Gpt4 M2.0 is an open-source language model by jondurbin. Features: 65b LLM, VRAM: 130.4GB, Context: 2K, License: cc-by-nc-4.0, LLM Explorer Score: 0.11, Arc: 65.1, HellaSwag: 86.3, MMLU: 64.3, GSM8K: 21.6.

Dataset:jondurbin/airoboros-gp... Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/jondurbin/airoboros-65b-gpt4-m2.0

Airoboros 65B Gpt4 M2.0 Benchmarks

ARC: 65.1 vs 96.7 (so35)^-32.7%

HellaSwag: 86.34 vs 95.3 (gpt4)^-9.4%

MMLU: 64.32 vs 88.3 (so35)^-27.2%

GSM8K: 21.61 vs 96.4 (so35)^-77.6%

LLME Score: 0.11174

^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)

Airoboros 65B Gpt4 M2.0 (jondurbin/airoboros-65b-gpt4-m2.0)

🌟 Advertise your project 🚀

Airoboros 65B Gpt4 M2.0 Parameters and Internals

Model Type

text generation

Additional Notes

The model integrates OpenAI's outputs and is not intended to compete with OpenAI products. Avoid commercial usage due to potential ToS conflicts.

Training Details

Data Sources:

OpenAI API calls to GPT-4 via airoboros

Input Output

Input Format:

A chat between a user and an assistant with specified delimiters for context and instructions.

Accepted Modalities:

text

Output Format:

Structured-text responses based on user prompts

Performance Tips:

Use explicit delimiters to assist the model in contextual responses. For closed-context instructions, use designated block formats.

LLM Name	Airoboros 65B Gpt4 M2.0
Repository 🤗	https://huggingface.co/jondurbin/airoboros-65b-gpt4-m2.0
Model Size	65b
Required VRAM	130.4 GB
Updated	2026-05-17
Maintainer	jondurbin
Model Type	llama
Model Files	9.9 GB: 1-of-14 9.7 GB: 2-of-14 9.7 GB: 3-of-14 9.7 GB: 4-of-14 9.7 GB: 5-of-14 9.7 GB: 6-of-14 9.7 GB: 7-of-14 9.7 GB: 8-of-14 9.7 GB: 9-of-14 9.7 GB: 10-of-14 9.7 GB: 11-of-14 9.7 GB: 12-of-14 9.7 GB: 13-of-14 4.1 GB: 14-of-14
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.31.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Quantized Models of the Airoboros 65B Gpt4 M2.0

Model	Likes	Downloads	VRAM
Airoboros 65B GPT4 M2.0 GPTQ	2	24	33 GB
Airoboros 65B GPT4 M2.0 GGML	2	5	27 GB

Best Alternatives to Airoboros 65B Gpt4 M2.0

Best Alternatives	Context / RAM	Downloads	Likes
Lite Oute 1 65M Instruct	2K / 0.3 GB	17	12
Lite Oute 1 65M	2K / 0.3 GB	20	11
StableBeluga1 Delta	2K / 130.4 GB	218	57
Airoboros 65B Gpt4 2.0	2K / 130.4 GB	1008	0
Openbuddy Llama 65B V8 Bf16	2K / 130.6 GB	1025	9
UltraLM 65B	2K / 130.4 GB	1062	9
Llama 65B Instruct	2K / 130.4 GB	1036	15
Airoboros 65B Gpt4 1.4	2K / 130.4 GB	925	17
Airoboros 65B Gpt4 1.3	2K / 130.4 GB	999	1
Airoboros 65B Gpt4 1.2	2K / 130.4 GB	847	22

Note: green Score (e.g. "73.2") means that the model is better than jondurbin/airoboros-65b-gpt4-m2.0.

Rank the Airoboros 65B Gpt4 M2.0 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? 53999 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

Airoboros 65B Gpt4 M2.0 by jondurbin