What are the hardware requirements for OLMo 7B SFT?

OLMo 7B SFT requires approximately 13.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OLMo 7B SFT and how large is it?

OLMo 7B SFT is developed by allenai, a model with 7b 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 OLMo 7B SFT?

OLMo 7B SFT is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OLMo 7B SFT by allenai — VRAM 13.7GB

Name: OLMo 7B SFT
Author: allenai

OLMo 7B SFT is an open-source language model by allenai. Features: 7b LLM, VRAM: 13.7GB, License: apache-2.0, LLM Explorer Score: 0.11.

Arxiv:2402.00838 Conversational Custom code Dataset:allenai/dolma Dataset:allenai/tulu-v2-sft-mi... En Hf olmo Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/allenai/OLMo-7B-SFT

OLMo 7B SFT Parameters and Internals

Model Type

Transformer style autoregressive language model

Additional Notes

Installation requires `ai2-olmo`. Use with HuggingFace Transformers<=4.39 for compatibility.

Supported Languages

en (Proficient)

Training Details

Data Sources:

allenai/dolma, allenai/tulu-v2-sft-mixture, allenai/ultrafeedback_binarized_cleaned

Data Volume:

2.5 Trillion Tokens

Methodology:

SFT

Context Length:

2048

Model Architecture:

Based on OLMo core architecture.

Responsible Ai Considerations

Accountability:

Users are responsible for the outputs produced by the model.

Mitigation Strategies:

Developers should consider implementing safeguards for biases, privacy, and other potential harms.

LLM Name	OLMo 7B SFT
Repository 🤗	https://huggingface.co/allenai/OLMo-7B-SFT
Model Size	7b
Required VRAM	13.7 GB
Updated	2026-07-09
Maintainer	allenai
Model Type	hf_olmo
Model Files	9.9 GB: 1-of-2 3.8 GB: 2-of-2
Supported Languages	en
Model Architecture	OLMoForCausalLM
License	apache-2.0
Transformers Version	4.35.0.dev0
Tokenizer Class	OLMoTokenizer
Padding Token	<\|padding\|>
Vocabulary Size	50280
Torch Data Type	bfloat16

Rank the OLMo 7B SFT 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 OLMo 7B SFT

Best Alternatives	Context / RAM	Downloads	Likes
OLMo 7B Instruct	0K / 13.7 GB	475	53
OLMo 7B	0K / 27.6 GB	2343	653
OLMo 7B 0424	0K / 27.6 GB	108	51
OLMo 1.7 7B	0K / 27.6 GB	46	43
OLMo 7B Twin 2T	0K / 27.6 GB	651	22

Note: green Score (e.g. "73.2") means that the model is better than allenai/OLMo-7B-SFT.