What are the hardware requirements for Airoboros L2 C70b 3.1.2?

Airoboros L2 C70b 3.1.2 requires approximately 138 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Airoboros L2 C70b 3.1.2 and how large is it?

Airoboros L2 C70b 3.1.2 is developed by jondurbin, a model with 69b 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 Airoboros L2 C70b 3.1.2?

Airoboros L2 C70b 3.1.2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Airoboros L2 C70b 3.1.2 by jondurbin — VRAM 138GB, 4K context

Name: Airoboros L2 C70b 3.1.2
Author: jondurbin

Airoboros L2 C70b 3.1.2 is an open-source language model by jondurbin. Features: 69b LLM, VRAM: 138GB, Context: 4K, License: llama2, LLM Explorer Score: 0.09.

Conversational Dataset:jondurbin/airoboros-3.... Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jondurbin/airoboros-l2-c70b-3.1.2

Airoboros L2 C70b 3.1.2 Parameters and Internals

Model Type

instruction following, general purpose

Use Cases

Primary Use Cases:

instruction following

Additional Notes

The model is uncensored and not suitable for casual chat/roleplay.

Training Details

Data Sources:

airoboros-3.1 dataset

Methodology:

fine-tuning on top of llama-2-70b-chat

Input Output

Performance Tips:

Use a very low temperature for better results in MathJSON and context obedient question answering.

LLM Name	Airoboros L2 C70b 3.1.2
Repository 🤗	https://huggingface.co/jondurbin/airoboros-l2-c70b-3.1.2
Model Size	69b
Required VRAM	138 GB
Updated	2026-07-09
Maintainer	jondurbin
Model Type	llama
Model Files	4.0 GB: 1-of-36 3.7 GB: 2-of-36 3.9 GB: 3-of-36 3.9 GB: 4-of-36 3.9 GB: 5-of-36 3.7 GB: 6-of-36 3.9 GB: 7-of-36 3.9 GB: 8-of-36 3.9 GB: 9-of-36 3.7 GB: 10-of-36 3.9 GB: 11-of-36 3.9 GB: 12-of-36 3.9 GB: 13-of-36 3.7 GB: 14-of-36 3.9 GB: 15-of-36 3.9 GB: 16-of-36 3.9 GB: 17-of-36 3.7 GB: 18-of-36 3.9 GB: 19-of-36 3.9 GB: 20-of-36 3.9 GB: 21-of-36 3.7 GB: 22-of-36 3.9 GB: 23-of-36 3.9 GB: 24-of-36 3.9 GB: 25-of-36 3.7 GB: 26-of-36 3.9 GB: 27-of-36 3.9 GB: 28-of-36 3.9 GB: 29-of-36 3.7 GB: 30-of-36 3.9 GB: 31-of-36 3.9 GB: 32-of-36 3.9 GB: 33-of-36 3.7 GB: 34-of-36 3.9 GB: 35-of-36 3.2 GB: 36-of-36
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Airoboros L2 C70b 3.1.2 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 Airoboros L2 C70b 3.1.2

Best Alternatives	Context / RAM	Downloads	Likes
...ine Tu Ophtho 3 1e 05 Stanford	4K / 138.7 GB	5	0
StableBeluga2	4K / 1.7 GB	15937	20
V Alpha Tross	4K / 138.7 GB	74	20
Uni TianYan V1	4K / 138 GB	66	0
SaiLy Experiment V1	4K / 276 GB	15	2
Model 007 Preview	4K / 138 GB	29	1
QCammel 70 X AWQ	4K / 36.6 GB	6	1
QCammel 70 X GPTQ	4K / 35.3 GB	10	2

Note: green Score (e.g. "73.2") means that the model is better than jondurbin/airoboros-l2-c70b-3.1.2.