Marketplace · Text & chat

olmo2:7b

Call olmo2:7b through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.06
per 1M output tokens
£1 buys about 17 million tokens (≈ 13 million words)
Hosts
1
Loaded now
0

At a glance.

  • Type: Text & chat
  • Hosts serving it now: 1 (0 with it loaded in memory)
  • Engines: ollama
  • Context window: up to 4,096 tokens
  • Rentable: a whole host from £0.04 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
    model="olmo2:7b",
    messages=[{"role": "user", "content": "Hello"}],
)

olmo2:7b in detail.

OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.

Published by
allenai
Parameters
7.3B
Download size
4.5 GB (as packaged for Ollama)
Quantisation
Q4_K_M
Format
gguf
Architecture
olmo2
Licence
Apache 2.0
Based on
allenai/OLMo-2-1124-7B-DPO
Task
text generation
Library
transformers
Languages
en
First published
18 Dec 2024
Last updated
6 Jan 2025
Downloads (30 days)
41,650 on Hugging Face
Likes
51

olmo2 text-generation en

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

OLMo-2-1124-7B-Instruct

NOTE: 1/3/2025 UPDATE:

Upon the initial release of OLMo-2 models, we realized the post-trained models did not share the pre-tokenization logic that the base models use. As a result, we have trained new post-trained models. The new models are available under the same names as the original models, but we have made the old models available with a postfix "-preview". See OLMo 2 Preview Post-trained Models for the colleciton of the legacy models.

Release Documentation

OLMo 2 7B Instruct November 2024 is post-trained variant of the OLMo-2 7B November 2024 model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset and further DPO training on this dataset, and finally RLVR training using this data. Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. Check out the OLMo 2 paper or Tülu 3 paper for more details!

OLMo is a series of Open Language Models designed to enable the science of language models. These models are trained on the Dolma dataset. We are releasing all code, checkpoints, logs (coming soon), and associated training details. The core models released in this batch include the following:

Model description

  • Model type: A model trained on a mix of publicly available, synthetic and human-created datasets.
  • Language(s) (NLP): Primarily English
  • License: Apache 2.0
  • Finetuned from model: allenai/OLMo-2-7B-1124-DPO
Read the rest of the model card

Model Sources

  • Project Page: https://allenai.org/olmo
  • Repositories:
  • Core repo (training, inference, fine-tuning etc.): https://github.com/allenai/OLMo
  • Evaluation code: https://github.com/allenai/olmes
  • Further fine-tuning code: https://github.com/allenai/open-instruct
  • Paper: https://arxiv.org/abs/2501.00656
  • Demo: https://playground.allenai.org/

Installation

OLMo 2 will be supported in the next version of Transformers, and you need to install it from the main branch using:

pip install --upgrade git+https://github.com/huggingface/transformers.git

Using the model

Loading with HuggingFace

To load the model with HuggingFace, use the following snippet:

from transformers import AutoModelForCausalLM

olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-7B-Instruct")

Chat template

The chat template for our models is formatted as:

<|endoftext|><|user|>\nHow are you doing?\n<|assistant|>\nI'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>

Or with new lines expanded:

<|endoftext|><|user|>
How are you doing?
<|assistant|>
I'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>

It is embedded within the tokenizer as well, for tokenizer.apply_chat_template.

System prompt

In Ai2 demos, we use this system prompt by default:

You are OLMo 2, a helpful and harmless AI Assistant built by the Allen Institute for AI.

The model has not been trained with a specific system prompt in mind.

Bias, Risks, and Limitations

The OLMo-2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). See the Falcon 180B model card for an example of this.

Performance

ModelAverageAlpacaEvalBBHDROPGSM8kIFEvalMATHMMLUSafetyPopQATruthQA
Open weights models
Gemma-2-9B-it51.943.72.558.879.769.929.869.175.528.361.4
Ministral-8B-Instruct52.131.456.256.280.056.440.068.556.220.255.5
Mistral-Nemo-Instruct-240750.945.854.623.681.464.531.970.052.726.957.7
Qwen-2.5-7B-Instruct57.129.725.354.483.874.769.976.675.018.163.1
Llama-3.1-8B-Instruct58.925.869.761.783.480.642.571.370.228.455.1
Tülu 3 8B60.434.066.062.687.682.443.768.275.429.155.0
Qwen-2.5-14B-Instruct60.834.634.050.583.982.470.681.179.321.170.8
Fully open models
OLMo-7B-Instruct28.25.235.330.714.332.22.146.354.017.144.5
OLMo-7B-0424-Instruct33.18.534.447.923.239.25.248.949.318.955.2
OLMoE-1B-7B-0924-Instruct35.58.537.234.347.246.28.451.651.620.649.1
MAP-Neo-7B-Instruct42.917.626.448.269.435.931.556.573.718.451.6
OLMo-2-7B-SFT50.210.249.759.674.666.925.361.182.123.648.6
OLMo-2-7B-DPO54.227.946.760.282.673.030.360.881.023.556.0
OLMo-2-13B-SFT55.311.559.671.376.368.629.568.082.329.457.1
OLMo-2-13B-DPO60.638.357.971.582.380.235.267.979.729.063.9
OLMo-2-7B-1124–Instruct54.829.146.660.585.172.332.561.380.623.256.5
OLMo-2-13B-1124-Instruct62.039.558.871.587.482.639.268.579.128.864.3

License and use

OLMo 2 is licensed under the Apache 2.0 license. OLMo 2 is intended for research and educational use. For more information, please see our Responsible Use Guidelines. This model has been fine-tuned using a dataset mix with outputs generated from third party models and are subject to additional terms: Gemma Terms of Use.

Citation

@article{olmo20242olmo2furious,
      title={2 OLMo 2 Furious}, 
      author={Team OLMo and Pete Walsh and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Shane Arora and Akshita Bhagia and Yuling Gu and Shengyi Huang and Matt Jordan and Nathan Lambert and Dustin Schwenk and Oyvind Tafjord and Taira Anderson and David Atkinson and Faeze Brahman and Christopher Clark and Pradeep Dasigi and Nouha Dziri and Michal Guerquin and Hamish Ivison and Pang Wei Koh and Jiacheng Liu and Saumya Malik and William Merrill and Lester James V. Miranda and Jacob Morrison and Tyler Murray and Crystal Nam and Valentina Pyatkin and Aman Rangapur and Michael Schmitz and Sam Skjonsberg and David Wadden and Christopher Wilhelm and Michael Wilson and Luke Zettlemoyer and Ali Farhadi and Noah A. Smith and Hannaneh Hajishirzi},
      year={2024},
      eprint={2501.00656},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.00656}, 
}

Sources: allenai/OLMo-2-1124-7B-Instruct on Hugging Face · olmo2:7b on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving olmo2:7b right now
HostTierPriceMeasured speedHealthStateRent
7B-A1B (5G)L1£0.03 in · £0.06 out5 tok/s · 214 ms first token82loads on request£0.04/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

Right now one machine serves olmo2:7b. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
1
0 loaded in memory
Price to beat
£0.06
per 1M output tokens
Fastest measured
5 tok/s

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load olmo2:7b, and the platform benchmarks it on your hardware before your first request.