What are the hardware requirements for OLMo 2 0425 1B Instruct?

OLMo 2 0425 1B Instruct requires approximately 3 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OLMo 2 0425 1B Instruct and how large is it?

OLMo 2 0425 1B Instruct is developed by allenai, a model with 1b 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 2 0425 1B Instruct?

OLMo 2 0425 1B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OLMo 2 0425 1B Instruct by allenai — VRAM 3GB, 4K context

Name: OLMo 2 0425 1B Instruct
Author: allenai

OLMo 2 0425 1B Instruct is an open-source language model by allenai. Features: 1b LLM, VRAM: 3GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.24.

Arxiv:2411.15124 Arxiv:2501.00656 Base model:allenai/olmo-2-0425... Base model:finetune:allenai/ol... Conversational Dataset:allenai/rlvr-math En Endpoints compatible Instruct Olmo2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/allenai/OLMo-2-0425-1B-Instruct

OLMo 2 0425 1B Instruct Parameters and Internals

LLM Name	OLMo 2 0425 1B Instruct
Repository 🤗	https://huggingface.co/allenai/OLMo-2-0425-1B-Instruct
Base Model(s)	OLMo 2 0425 1B RLVR1 allenai/OLMo-2-0425-1B-RLVR1
Model Size	1b
Required VRAM	3 GB
Updated	2026-08-02
Maintainer	allenai
Model Type	olmo2
Instruction-Based	Yes
Model Files	3.0 GB
Supported Languages	en
Model Architecture	Olmo2ForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.50.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the OLMo 2 0425 1B Instruct 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

Quantized Models of the OLMo 2 0425 1B Instruct

Model	Likes	Downloads	VRAM
OLMo 2 0425 1B Instruct GGUF	8	966	0 GB
...Mo 2 0425 1B Instruct Bnb 4bit	0	40	1 GB

Best Alternatives to OLMo 2 0425 1B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
...man Structured Output Olmo2 1B	4K / 3 GB	9	0
OLMo 2 0425 1B Instruct	4K / 3 GB	708	3
...Mo 2 0425 1B Instruct Bnb 4bit	4K / 1.4 GB	40	0
OLMo 2 0425 1B Instruct GGUF	4K / 0.5 GB	966	8