Back to Models
allenai/molmo-2-8b
Not Available

Molmo2 8B

Molmo2-8B is an open vision-language model developed by the Allen Institute for AI (Ai2) as part of the Molmo2 family, supporting image, video, and multi-image understanding and grounding. It is based on Qwen3-8B and uses SigLIP 2 as its vision backbone, outperforming other open-weight, open-data models on short videos, counting, and captioning, while remaining competitive on long-video tasks.

1/9/2026
36,864 tokens
#117 Vision (Overall)

Specifications

Modalities

Input
text
image
video
Output
text

Supported Parameters

frequency_penalty
logit_bias
max_tokens
presence_penalty
repetition_penalty
seed
stop
temperature
top_k
top_p

Max Output Tokens

36,864

Frequently asked questions

Is Molmo2 8B available on FastMetal?
Not at the moment. GLM 5.3 Flash, from the same lab, is available on the FastMetal API today.
What is the context window of Molmo2 8B?
36,864 tokens, shared between the prompt and the response.
How does Molmo2 8B rank?
#233 on the public arena's Overall board (ELO 1,328). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,328
#233
EnglishELO: 1,340
#242
Instruction FollowingELO: 1,310
#240
Hard PromptsELO: 1,339
#228
Vision
OverallELO: 1,107
#117