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.
ollama run olmo2
Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.
Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.
| Etiket | Boyut | Bağlam | Girdi | Komut |
|---|---|---|---|---|
| latest | 4.5GB | 4K | Text |
ollama run olmo2:latest
|
| 7b | 4.5GB | 4K | Text |
ollama run olmo2:7b
|
| 13b | 8.4GB | 4K | Text |
ollama run olmo2:13b
|
| 7b-1124-instruct-q4_K_M | 4.5GB | 4K | Text |
ollama run olmo2:7b-1124-instruct-q4_K_M
|
| 7b-1124-instruct-q8_0 | 7.8GB | 4K | Text |
ollama run olmo2:7b-1124-instruct-q8_0
|
| 7b-1124-instruct-fp16 | 15GB | 4K | Text |
ollama run olmo2:7b-1124-instruct-fp16
|
| 13b-1124-instruct-q4_K_M | 8.4GB | 4K | Text |
ollama run olmo2:13b-1124-instruct-q4_K_M
|
| 13b-1124-instruct-q8_0 | 15GB | 4K | Text |
ollama run olmo2:13b-1124-instruct-q8_0
|
| 13b-1124-instruct-fp16 | 27GB | 4K | Text |
ollama run olmo2:13b-1124-instruct-fp16
|
Note: this model requires Ollama 0.5.5
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.