What are the hardware requirements for OLMo 2 1124 13B?

OLMo 2 1124 13B requires approximately 55.1 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 1124 13B and how large is it?

OLMo 2 1124 13B is developed by allenai, a model with 13b 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 1124 13B?

OLMo 2 1124 13B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OLMo 2 1124 13B by allenai — VRAM 55.1GB, 4K context

Name: OLMo 2 1124 13B
Author: allenai

OLMo 2 1124 13B is an open-source language model by allenai. Features: 13b LLM, VRAM: 55.1GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.2.

Arxiv:2501.00656 Dataset:allenai/dolmino-mix-11... Dataset:allenai/olmo-mix-1124 En Olmo2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/allenai/OLMo-2-1124-13B

OLMo 2 1124 13B Parameters and Internals

Model Type

Transformer, Autoregressive Language Model

Use Cases

Areas:

Research, Academic Benchmarks

Limitations:

Can generate harmful or sensitive content without proper safety filtering., Inaccuracies in generated statements; facts need verification.

Supported Languages

en ()

Training Details

Data Sources:

OLMo-Mix-1124, Dolmino-Mix-1124

Data Volume:

5 Trillion (Stage 1) & 843B (Stage 2) tokens

Responsible Ai Considerations

Fairness:

Models can generate harmful and sensitive content if not properly managed.

Mitigation Strategies:

Users advised to consider risks of misuse.

Input Output

Input Format:

AutoTokenizer: Tokenized input.

Accepted Modalities:

text

Output Format:

Decodable text response.

Performance Tips:

Using CUDA and quantization can enhance performance.

LLM Name	OLMo 2 1124 13B
Repository 🤗	https://huggingface.co/allenai/OLMo-2-1124-13B
Model Size	13b
Required VRAM	55.1 GB
Updated	2026-07-28
Maintainer	allenai
Model Type	olmo2
Model Files	4.9 GB: 1-of-12 5.0 GB: 2-of-12 5.0 GB: 3-of-12 5.0 GB: 4-of-12 4.8 GB: 5-of-12 4.8 GB: 6-of-12 4.8 GB: 7-of-12 5.0 GB: 8-of-12 5.0 GB: 9-of-12 5.0 GB: 10-of-12 3.7 GB: 11-of-12 2.1 GB: 12-of-12
Supported Languages	en
Model Architecture	Olmo2ForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.47.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352
Torch Data Type	float32

Rank the OLMo 2 1124 13B 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 1124 13B

Best Alternatives	Context / RAM	Downloads	Likes
OLMo 2 1124 13B Instruct	4K / 27.4 GB	12506	48
OLMo 2 1124 13B SFT	4K / 27.4 GB	707	0
OLMo 2 1124 13B DPO	4K / 27.4 GB	638	0
...Mo 2 1124 13B Instruct Preview	4K / 27.4 GB	75	58
OLMo 2 1124 13B Instruct RLVR2	4K / 27.4 GB	26	0
OLMo 2 1124 13B SFT Preview	4K / 27.4 GB	73	3
OLMo 2 1124 13B DPO Preview	4K / 27.4 GB	59	3

Note: green Score (e.g. "73.2") means that the model is better than allenai/OLMo-2-1124-13B.