Moondream

3 indexed models

3 matching models

Moondream: Moondream 3.1

moondream/moondream3.1-9b-a2b-20261013

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with a 32K-token context and an opt

Context window
32,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, visionInput

Inference prices

Moondream: Moondream 3 Preview

moondream/moondream3-preview-20261013

Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with a 32K-token context and an optional reasoning mode.

Context window
32,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, visionInput

Inference prices

Moondream: Parakeet Ultra

moondream/parakeet-ultra-20261102

Parakeet Ultra is Moondream's post-trained version of NVIDIA's Parakeet TDT 0.6B v3 speech-to-text model, with the same architecture, tokenizer, and 0.6B parameters. It lowers word error rate on the Open ASR Leaderboard English sets (5.80% vs 6.26%) and the 25-language FLEURS set

Context window
0
Input modalities
audio
Output modalities
transcription
Capabilities
audioInput

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace