Compare
OLMo 2 1124 7B Instruct vs OLMo 2 0325 32B Instruct
Put two to four models side by side on the fields that decide a deployment: context, price, region, license, languages, hosting, and what is verified.
| OLMo 2 1124 7B Instruct | OLMo 2 0325 32B Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Allen Institute for AI (Ai2) |
| Parameters | 7.3B | 32.2B |
| Context window | Not verified: the provider has not documented this claim. | Not verified: the provider has not documented this claim. |
| License | apache-2.0 | apache-2.0 |
| Modalities | text | text |
| Release date | 18 Dec 2024 | 12 Mar 2025 |
| Languages | Strong: en Adequate: — | Strong: en Adequate: — |
| Open weights | yes | yes |
| Tasks | Reasoning, Summarisation | Reasoning, Summarisation |
Where two models differ, this table shows the difference and stops. LLM EU publishes no winner badge without a documented score for that task, and a missing figure stays missing instead of becoming a zero.
When to use it
OLMo 2 1124 7B Instruct
Strengths
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- Apache-2.0 licence, so commercial self-hosting is permitted without a separate agreement
- at 7.3B parameters it fits on a single accelerator
- the model page lists en
- instruction-tuned checkpoint with a chat template in the repository
Limits
- catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 7.3B parameters, the weights fit on a single modest accelerator
Tasks
OLMo 2 0325 32B Instruct
Strengths
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- Apache-2.0 licence, so commercial self-hosting is permitted without a separate agreement
- the model page lists en
- instruction-tuned checkpoint with a chat template in the repository
Limits
- catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 32.2B parameters, self-hosting needs a high-memory accelerator
Tasks
Tasks: Reasoning, Summarisation