What are the hardware requirements for OLMo 2 0325 32B Instruct?

OLMo 2 0325 32B Instruct requires approximately 64.7 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 0325 32B Instruct and how large is it?

OLMo 2 0325 32B Instruct is developed by unsloth, a model with 32b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does OLMo 2 0325 32B Instruct perform on standard benchmarks?

OLMo 2 0325 32B Instruct has the following published scores: LMSYS ELO 1251. Compare against reference models on this page or on the LLM Explorer leaderboards.

OLMo 2 0325 32B Instruct by unsloth — VRAM 64.7GB, 4K context

Name: OLMo 2 0325 32B Instruct
Author: unsloth

OLMo 2 0325 32B Instruct is an open-source language model by unsloth. Features: 32b LLM, VRAM: 64.7GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.3, ELO: 1251.

Arxiv:2411.15124 Arxiv:2501.00656 Base model:allenai/olmo-2-0325... Base model:finetune:allenai/ol... Conversational Dataset:allenai/tulu-3-sft-olm... En Endpoints compatible Instruct Olmo2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/unsloth/OLMo-2-0325-32B-Instruct

OLMo 2 0325 32B Instruct Benchmarks

LMSys ELO 1251 vs 1272 (so35) -1.7%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

OLMo 2 0325 32B Instruct Parameters and Internals

LLM Name	OLMo 2 0325 32B Instruct
Repository 🤗	https://huggingface.co/unsloth/OLMo-2-0325-32B-Instruct
Base Model(s)	OLMo 2 0325 32B Instruct allenai/OLMo-2-0325-32B-Instruct
Model Size	32b
Required VRAM	64.7 GB
Updated	2026-08-03
Maintainer	unsloth
Model Type	olmo2
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-14 4.9 GB: 2-of-14 4.9 GB: 3-of-14 4.9 GB: 4-of-14 4.9 GB: 5-of-14 4.9 GB: 6-of-14 4.9 GB: 7-of-14 4.9 GB: 8-of-14 4.9 GB: 9-of-14 4.9 GB: 10-of-14 4.9 GB: 11-of-14 4.9 GB: 12-of-14 4.8 GB: 13-of-14 1.0 GB: 14-of-14
Supported Languages	en
Model Architecture	Olmo2ForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.50.0.dev0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the OLMo 2 0325 32B 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

Best Alternatives to OLMo 2 0325 32B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
OLMo 2 0325 32B Instruct	4K / 64.7 GB	4110	147
OLMo 2 0325 32B DPO	4K / 64.7 GB	364	3
OLMo 2 Instruct Math 32B	4K / 64.7 GB	22	5
...o 2 0325 32B Instruct Bnb 4bit	4K / 18.3 GB	9	1
OLMo 2 0325 32B Instruct 4bit	4K / 18.1 GB	46	10
OLMo 2 0325 32B Instruct GGUF	4K / 12 GB	1325	12

Note: green Score (e.g. "73.2") means that the model is better than unsloth/OLMo-2-0325-32B-Instruct.