Molmo2-8B
Ai2- Arena score
- 1287
- Among open models
- #91of 148
- Among all on Arena
- #266
- Votes
- 819
Measured on Molmo 2 8B, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Software & IT1299#91#265292
- English1299#96#274330
- Hard prompts1287#87#258449
- Non-English1274#84#256489
- Instructions1270#86#259219
- Excluding ties1218#91#265595
About as strong, smaller
Compare
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiomu2solutions/Molmo2-8B-GGUF1 build
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/Molmo2-8B-mxfp41 build
Most downloaded
BenchClub runs
Not runnable yet
Runs open once a Molmo2-8B build is registered.
More from Ai2
See more
Olmo-3.1-32B-Instruct21.3K32.2B

Olmo-3-32B-Think11.8K32.2B

Olmo-3.1-32B-Think7.7K32.2B

Llama-3.1-Tulu-3-8B6K8.0B
Other 3–9B models
See more
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA1.9M4.0B
granite-4.1-8bIBM Granite79.4K8.8B
Spark-X2.6-4BXHToken32.9K4.1B
tiny-aya-globalCohere Labs31.7K3.3B