What are the hardware requirements for Opt Iml Max 30B?

Opt Iml Max 30B requires approximately 60.1 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 Opt Iml Max 30B and how large is it?

Opt Iml Max 30B is developed by facebook, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Opt Iml Max 30B perform on standard benchmarks?

Opt Iml Max 30B has the following published scores: MMLU 41.09. Compare against reference models on this page or on the LLM Explorer leaderboards.

Opt Iml Max 30B by facebook — VRAM 60.1GB, 2K context

Name: Opt Iml Max 30B
Author: facebook

Opt Iml Max 30B is an open-source language model by facebook. Features: 30b LLM, VRAM: 60.1GB, Context: 2K, License: other, LLM Explorer Score: 0.09, Arc: 43.9, HellaSwag: 72.4, MMLU: 41.1, GSM8K: 2.5.

Arxiv:2212.12017 Opt Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/facebook/opt-iml-max-30b

Opt Iml Max 30B Parameters and Internals

Model Type

text-generation, instruction-tuning

Use Cases

Areas:

Research, NLP task evaluation

Limitations:

Factual correctness, Generation of toxic language, Enforcing stereotypes

Training Details

Data Sources:

OPT-IML Bench, including Super-NaturalInstructions, FLAN, PromptSource

Data Volume:

2 billion tokens

Methodology:

Instruction Meta-Learning

Context Length:

2048

Hardware Used:

64 40GB A100 GPUs

Model Architecture:

Fine-tuning of OPT models using instruction-tuning

Responsible Ai Considerations

Fairness:

The model is susceptible to biases and enforcing stereotypes.

Mitigation Strategies:

Usage should be accompanied with responsible best practices.

Input Output

Input Format:

Sequences of 2048 consecutive tokens

Accepted Modalities:

text

Output Format:

Text generation

Performance Tips:

Load model in half-precision to optimize memory on GPU.

LLM Name	Opt Iml Max 30B
Repository 🤗	https://huggingface.co/facebook/opt-iml-max-30b
Model Size	30b
Required VRAM	60.1 GB
Updated	2026-07-28
Maintainer	facebook
Model Type	opt
Model Files	9.8 GB: 1-of-7 9.9 GB: 2-of-7 9.9 GB: 3-of-7 9.9 GB: 4-of-7 9.9 GB: 5-of-7 9.9 GB: 6-of-7 0.8 GB: 7-of-7
Model Architecture	OPTForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.22.2
Beginning of Sentence Token	</s>
End of Sentence Token	</s>
Unk Token	</s>
Vocabulary Size	50272
Torch Data Type	float16
Activation Function	relu
Errors	replace

Rank the Opt Iml Max 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 Opt Iml Max 30B

Best Alternatives	Context / RAM	Downloads	Likes
Galpaca 30B MiniOrca	2K / 59.6 GB	48	1
Opt 30B	2K / 60.1 GB	14167	137
Galpaca 30B	2K / 60.8 GB	59	55
OPT 30B Erebus	2K / 36 GB	60	67
...alactica 30B Evol Instruct 70K	2K / 60.1 GB	57	23
Opt Iml 30B	2K / 60.1 GB	36	73
Galactica 30B	2K / 60.8 GB	71	40
Dalio Io 30B Cp1500	2K / 121.7 GB	11	0
Galactica 30B	2K / GB	19	1
...h 1e 5 Lr Handwritten Complete	2K / 121.7 GB	18	0

Note: green Score (e.g. "73.2") means that the model is better than facebook/opt-iml-max-30b.