What are the hardware requirements for Airoboros Jamba 3 3?

Airoboros Jamba 3 3 requires approximately 103.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Airoboros Jamba 3 3 and how large is it?

Airoboros Jamba 3 3 is developed by jondurbin, a model with 51.6b 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 Jamba 3 3?

Airoboros Jamba 3 3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Airoboros Jamba 3 3 by jondurbin — VRAM 103.6GB

Name: Airoboros Jamba 3 3
Author: jondurbin

Airoboros Jamba 3 3 is an open-source language model by jondurbin. Features: 51.6b LLM, VRAM: 103.6GB, License: apache-2.0, LLM Explorer Score: 0.12.

Conversational Custom code Dataset:bluemoon-fandom-1-1-rp... Dataset:boolq Dataset:glaiveai/glaive-functi... Dataset:grimulkan/limarp-augme... Dataset:jondurbin/airoboros-3.... Dataset:jondurbin/cinematika-v... Dataset:jondurbin/gutenberg-dp... Dataset:ldjnr/capybara Dataset:mattpscott/airoboros-s... Dataset:piqa Dataset:unalignment/toxic-dpo-... Dataset:vezora/tested-22k-pyth... Endpoints compatible Jamba Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jondurbin/airoboros-jamba-3-3

Airoboros Jamba 3 3 Parameters and Internals

Model Type

text generation

Additional Notes

Using explicit delimiters helps the model understand context associations better.

Training Details

Data Sources:

jondurbin/airoboros-3.2, bluemoon-fandom-1-1-rp-cleaned, boolq, jondurbin/gutenberg-dpo-v0.1, LDJnr/Capybara, jondurbin/cinematika-v0.1, glaiveai/glaive-function-calling-v2, grimulkan/LimaRP-augmented, piqa, Vezora/Tested-22k-Python-Alpaca, mattpscott/airoboros-summarization, unalignment/toxic-dpo-v0.2

Data Volume:

8192 context length

Methodology:

QLoRA fine-tuning

Context Length:

8192

Input Output

Input Format:

LLaMA-2 chat format

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use a very low temperature for context-obedient question answering.

LLM Name	Airoboros Jamba 3 3
Repository 🤗	https://huggingface.co/jondurbin/airoboros-jamba-3-3
Model Size	51.6b
Required VRAM	103.6 GB
Updated	2026-08-06
Maintainer	jondurbin
Model Type	jamba
Model Files	3.9 GB: 1-of-27 4.0 GB: 2-of-27 4.0 GB: 3-of-27 3.9 GB: 4-of-27 3.9 GB: 5-of-27 3.9 GB: 6-of-27 4.0 GB: 7-of-27 4.0 GB: 8-of-27 4.0 GB: 9-of-27 4.0 GB: 10-of-27 3.9 GB: 11-of-27 4.0 GB: 12-of-27 4.0 GB: 13-of-27 4.0 GB: 14-of-27 4.0 GB: 15-of-27 4.0 GB: 16-of-27 3.9 GB: 17-of-27 4.0 GB: 18-of-27 4.0 GB: 19-of-27 4.0 GB: 20-of-27 4.0 GB: 21-of-27 4.0 GB: 22-of-27 3.9 GB: 23-of-27 4.0 GB: 24-of-27 4.0 GB: 25-of-27 3.8 GB: 26-of-27 0.5 GB: 27-of-27
Model Architecture	JambaForCausalLM
License	apache-2.0
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Padding Token	<\|pad\|>
Vocabulary Size	65536
Torch Data Type	bfloat16

Rank the Airoboros Jamba 3 3 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 Jamba 3 3

Best Alternatives	Context / RAM	Downloads	Likes
AI21 Jamba2 Mini	256K / 103.3 GB	228	56
Jamba V0.1	256K / 103.4 GB	1833	1194
Jamba V0.1 Claude Chat	256K / 103.4 GB	5	3
Jamba V0.1 Hf	256K / 103.4 GB	5	3
Code Jamba V0.1	0K / 103.4 GB	6	7
Bagel Jamba V05	0K / 103.6 GB	11	7
Jamba V0.1 Chat Multilingual	0K / 103.4 GB	15	24

Note: green Score (e.g. "73.2") means that the model is better than jondurbin/airoboros-jamba-3-3.