What are the hardware requirements for Opt Flan Iml 6.7B?

Opt Flan Iml 6.7B requires approximately 26.6 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 Flan Iml 6.7B and how large is it?

Opt Flan Iml 6.7B is developed by MayaPH, a model with 6.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Opt Flan Iml 6.7B perform on standard benchmarks?

Opt Flan Iml 6.7B has the following published scores: MMLU 25.12. Compare against reference models on this page or on the LLM Explorer leaderboards.

Opt Flan Iml 6.7B by MayaPH — VRAM 26.6GB, 2K context

Name: Opt Flan Iml 6.7B
Author: MayaPH

Opt Flan Iml 6.7B is an open-source language model by MayaPH. Features: 6.7b LLM, VRAM: 26.6GB, Context: 2K, License: cc-by-sa-4.0, Instruction-Based, LLM Explorer Score: 0.12, Arc: 30.1, HellaSwag: 58.8, MMLU: 25.1.

Arxiv:2212.12017 Cot Dataset:sirneural/flan v2 Instruct Instruction Opt Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/MayaPH/opt-flan-iml-6.7b

Opt Flan Iml 6.7B Parameters and Internals

Model Type

Instruction Meta-Learning, Text Generation

Use Cases

Areas:

Research, Commercial

Applications:

Text Generation, General AI Tasks

Primary Use Cases:

Instruction Following, Task Automation

Limitations:

Low performance on GSM8K benchmark

Supported Languages

English (Unknown proficiency)

Training Details

Data Sources:

FLAN v2

Methodology:

Fine-tuning

Model Architecture:

Patterned after OPT + Instruction Meta-Learning

Input Output

Input Format:

Text Prompt

Accepted Modalities:

Text

Output Format:

Text

Performance Tips:

Use torch.float16 for faster processing and ensure correct tokenizer.

LLM Name	Opt Flan Iml 6.7B
Repository 🤗	https://huggingface.co/MayaPH/opt-flan-iml-6.7b
Model Size	6.7b
Required VRAM	26.6 GB
Updated	2026-07-15
Maintainer	MayaPH
Model Type	opt
Instruction-Based	Yes
Model Files	10.0 GB: 1-of-3 9.9 GB: 2-of-3 6.7 GB: 3-of-3 10.0 GB: 1-of-3 9.9 GB: 2-of-3 6.7 GB: 3-of-3
Model Architecture	OPTForCausalLM
License	cc-by-sa-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.32.0.dev0
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	</s>
End of Sentence Token	</s>
Unk Token	</s>
Vocabulary Size	50272
Torch Data Type	float32
Activation Function	relu
Errors	replace

Rank the Opt Flan Iml 6.7B 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 Flan Iml 6.7B

Best Alternatives	Context / RAM	Downloads	Likes
Galactica 6.7B EssayWriter	2K / 13.4 GB	55	5
...lactica 6.7B Evol Instruct 70K	2K / 27.4 GB	129	19
OPI Galactica 6.7B	2K / 13.4 GB	116	6
Ev Glaive Math	2K / 27.4 GB	6	0
Ev Glaive Math1	2K / 27.4 GB	5	0
Open Instruct Opt 6.7B Tulu	2K / 26.6 GB	43	2
LongForm OPT 6.7B	2K / 13.3 GB	15	4
...PT 6.7B Erebus Instruct Follow	2K / 13.8 GB	11	3

Note: green Score (e.g. "73.2") means that the model is better than MayaPH/opt-flan-iml-6.7b.