Comparar
OLMo 2 0425 1B Instruct vs OLMo 2 0325 32B Instruct
Ponga de dos a cuatro modelos lado a lado según los campos que deciden un despliegue: contexto, precio, región, licencia, idiomas, alojamiento y qué está verificado.
| OLMo 2 0425 1B Instruct | OLMo 2 0325 32B Instruct | |
|---|---|---|
| Proveedor | Allen Institute for AI (Ai2) | Allen Institute for AI (Ai2) |
| Parámetros | 1.5B | 32.2B |
| Ventana de contexto | Sin verificar: el proveedor no ha documentado esta afirmación. | Sin verificar: el proveedor no ha documentado esta afirmación. |
| Licencia | apache-2.0 | apache-2.0 |
| Modalidades | text | text |
| Fecha de publicación | 29 abr 2025 | 12 mar 2025 |
| Idiomas | Sólido: en Adecuado: — | Sólido: en Adecuado: — |
| Pesos abiertos | sí | sí |
| Tareas | Bajo coste, Resumen | Razonamiento, Resumen |
Cuando dos modelos difieren, esta tabla muestra la diferencia y se detiene. LLM EU no publica ninguna insignia de ganador sin una puntuación documentada para esa tarea, y una cifra faltante sigue faltando en lugar de convertirse en un cero.
Cuándo usarlo
OLMo 2 0425 1B Instruct
Puntos fuertes
- 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 1.5B parameters it fits on a single accelerator
- the model page lists en
- instruction-tuned checkpoint with a chat template in the repository
Límites
- 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 1.5B parameters, the weights fit on a single modest accelerator
Tareas
OLMo 2 0325 32B Instruct
Puntos fuertes
- 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
Límites
- 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
Tareas
Tareas: Resumen
Comparar modelos
Comparar modelos →- Bloom 1b1 vs OLMo 2 0425 1B Instruct
- Command R (08-2024) vs OLMo 2 0325 32B Instruct
- NVIDIA Cosmos Reason2 2B vs OLMo 2 0425 1B Instruct
- DeepSeek R1 Distill Qwen 1.5B vs OLMo 2 0425 1B Instruct
- DeepSeek-R1-Distill-Qwen-32B vs OLMo 2 0325 32B Instruct
- Devstral Small 2 (24B) vs OLMo 2 0325 32B Instruct