1.4M Downloads Updated 4 months ago
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.
7b
13b
9 models
olmo2:latest
4208d3b406db • 4.5GB •
4K context window •
Text input •
4 months ago
Text input •
4 months ago
4208d3b406db · 4 months ago
olmo2:7b
latest
4208d3b406db • 4.5GB •
4K context window •
Text input •
4 months ago
Text input •
4 months ago
4208d3b406db · 4 months ago
olmo2:13b
6c279ebc980f • 8.4GB •
4K context window •
Text input •
4 months ago
Text input •
4 months ago
6c279ebc980f · 4 months ago
olmo2:7b-1124-instruct-q4_K_M
4208d3b406db • 4.5GB •
4K context window •
Text input •
4 months ago
Text input •
4 months ago
4208d3b406db · 4 months ago
olmo2:7b-1124-instruct-q8_0
e75d0b293717 • 7.8GB •
4K context window •
Text input •
4 months ago
Text input •
4 months ago
e75d0b293717 · 4 months ago
olmo2:7b-1124-instruct-fp16
fa483f2d5cc7 • 15GB •
4K context window •
Text input •
4 months ago
Text input •
4 months ago
fa483f2d5cc7 · 4 months ago
olmo2:13b-1124-instruct-q4_K_M
6c279ebc980f • 8.4GB •
4K context window •
Text input •
4 months ago
Text input •
4 months ago
6c279ebc980f · 4 months ago
olmo2:13b-1124-instruct-q8_0
54d0ec72e884 • 15GB •
4K context window •
Text input •
4 months ago
Text input •
4 months ago
54d0ec72e884 · 4 months ago