Molmo2 8B is Allen AI's language model. An 8B open vision-language model from the Allen Institute for AI's Molmo 2 family, built on Qwen 3 architecture with strong image, video, and multi-image grounding capabilities.
Specifications
Canonical IDallenai-molmo-2-8b
TypeLanguage
StatusActive
CreatorAllen AIAllen AI
Input ModalitiesText
Output ModalitiesText
Parameters8B
Benchmarks
Intelligence Index
2.0
#468
GPQA
0.4
#362
HLE
0.0
#352
IFBench
0.3
#356
Time to First Token
SciCode
0.1
#387
LCR
0.0
#357
TerminalBench Hard
0.0
#350
TAU2
0.0
#373
Output TPS
0.0
#293

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Molmo2 8BCurrent
Molmo2 4BAvailable

Model IDs

accounts/fireworks/models/molmo2-8b
allenai-molmo-2-8b
molmo2-8b