Active Parameters
9B
Context Length
32K
Modality
Multimodal
Architecture
Mixture of Experts (MoE)
License
other
Release Date
30 Jun 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.30 · Output: $2.50
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
32,000 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
No evaluation benchmarks for Moondream 3.1 available.
Overall Rank
-
Coding Rank
-
Moondream 3.1 is an open-weight mixture-of-experts vision-language model with 9B total and 2B active parameters per token. It delivers efficient visual question answering, captioning, optical character recognition, and visual reasoning in constrained environments.
Mixture of Experts
Total Expert Parameters
2.0B
The Moondream model family developed by Moondream.
Assistant
Online