Molmo2-8B
Intelligence
7.3
#505/523
Coding
4.4
#387/429
Math
—
Speed
138 tok/s
TTFT: 441.00s
Pricing
—
Molmo2-8B is the Allen Institute for AI’s language model designed for various natural language processing tasks. It processes at 138.187 tokens per second, targeting professional users with a focus on coding and intelligence applications.
When to Use Molmo2-8B
✓ Best For
- Natural language understanding tasks
- Coding assistance
- Text generation and summarization
✗ Not Ideal For
- High-speed real-time applications
- Complex mathematical problem solving
How Molmo2-8B Compares
Intelligence Index · Higher is better
MistralCohereAllen Institute for AIIBMLiquid AI
Benchmark Profile
Coding Index
AlibabaGoogleAllen Institute for AIMeta
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (6)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 7.3 | |
| Coding Index | 4.4 | |
| GPQA | 425% | |
| HLE | 44% | |
| SciCode | 13.3% | |
| IFBench | 26.9% |
Data: Artificial Analysis · Updated: March 26, 2026
Frequently Asked Questions (15)
When was Molmo2-8B released?
Molmo2-8B was released on December 11, 2025.
Who created Molmo2-8B?
Molmo2-8B was created by Allen Institute for AI.
How intelligent is Molmo2-8B?
Molmo2-8B scores 7 on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 12).
How fast is Molmo2-8B?
Molmo2-8B generates output at 106.3 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
What is the latency of Molmo2-8B?
Molmo2-8B has a time to first token (TTFT) of 1.25s (based on the median across providers serving the model), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.47s).
How verbose is Molmo2-8B?
When evaluated on the Intelligence Index, Molmo2-8B generated 3.2M output tokens, which is better than average compared to other open weight non-reasoning models of similar size (median: 5.3M).
Is Molmo2-8B a reasoning model?
No, Molmo2-8B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Molmo2-8B support?
Molmo2-8B supports text, image, and video input.
What output modalities does Molmo2-8B support?
Molmo2-8B supports text output.
Can Molmo2-8B process images?
Yes, Molmo2-8B supports image input and can analyze, describe, and answer questions about images.
Is Molmo2-8B multimodal?
Yes, Molmo2-8B is multimodal. It can process text, image, and video input and generate text output.
What is the context window of Molmo2-8B?
Molmo2-8B has a context window of 37k tokens. This determines how much text and conversation history the model can process in a single request.
Is Molmo2-8B open source?
Yes, Molmo2-8B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Molmo2-8B have?
Molmo2-8B has 8.66 billion parameters.
What is the license for Molmo2-8B?
Molmo2-8B is released under the Apache 2.0 license. This license allows commercial use.
