What are the hardware requirements for Open Instruct Human Mix 30B?

Open Instruct Human Mix 30B requires approximately 130.5 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 Open Instruct Human Mix 30B and how large is it?

Open Instruct Human Mix 30B is developed by allenai, a model with 30b 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 Open Instruct Human Mix 30B?

Open Instruct Human Mix 30B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Open Instruct Human Mix 30B by allenai — VRAM 130.5GB, 2K context

Name: Open Instruct Human Mix 30B
Author: allenai

Open Instruct Human Mix 30B is an open-source language model by allenai. Features: 30b LLM, VRAM: 130.5GB, Context: 2K, Instruction-Based, LLM Explorer Score: 0.07.

Arxiv:2301.13688 Arxiv:2302.13971 Arxiv:2304.07327 Arxiv:2306.04751 Dataset:databricks/databricks-... Dataset:openassistant/oasst1 En Endpoints compatible Instruct Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/allenai/open-instruct-human-mix-30b

Open Instruct Human Mix 30B Parameters and Internals

Model Type

Instruction-tuned, Text generation

Supported Languages

en (Proficient)

Training Details

Data Sources:

FLAN V2, CoT, Dolly, Open Assistant 1

Methodology:

Finetuning

Model Architecture:

LLaMa

Input Output

Input Format:

<|user|> Your message here! <|assistant|>

Accepted Modalities:

text

Output Format:

text generation

Performance Tips:

Include a newline after `<|assistant|>` for better generation quality.

LLM Name	Open Instruct Human Mix 30B
Repository 🤗	https://huggingface.co/allenai/open-instruct-human-mix-30b
Model Size	30b
Required VRAM	130.5 GB
Updated	2026-08-05
Maintainer	allenai
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-14 9.7 GB: 2-of-14 9.8 GB: 3-of-14 10.0 GB: 4-of-14 9.8 GB: 5-of-14 9.9 GB: 6-of-14 9.9 GB: 7-of-14 9.8 GB: 8-of-14 10.0 GB: 9-of-14 9.8 GB: 10-of-14 9.9 GB: 11-of-14 9.9 GB: 12-of-14 9.8 GB: 13-of-14 2.3 GB: 14-of-14
Supported Languages	en
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.29.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32001
Torch Data Type	float32

Rank the Open Instruct Human Mix 30B 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 Open Instruct Human Mix 30B

Best Alternatives	Context / RAM	Downloads	Likes
Tildeopen 30B Mu Instruct	64K / 60.9 GB	41	6
...ct 2048 Open Platypus 100steps	2K / 65.2 GB	88	0
Llama 30B Instruct 2048	2K / 65.2 GB	374	103
...azarus Instruct PL Lora Unload	2K / 65.2 GB	85	0
Llama 30B Instruct	2K / 65.2 GB	333	24
...B 2048 Instruct PL Lora Unload	2K / 65.2 GB	97	1
...lama 30B Instruct 2048 PL Lora	2K / 65.2 GB	89	0
H2ogpt Oasst1 512 30B HF	2K / 65 GB	116	2
...pt Research Oig Oasst1 512 30B	2K / 81.1 GB	179	3
Veyra 30M Instruct	1K / 0.1 GB	151	3

Note: green Score (e.g. "73.2") means that the model is better than allenai/open-instruct-human-mix-30b.