moondream3.1-9B-A2B
Moondream 3.1 is a vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). It delivers state-of-the-art visual reasoning and detection while staying fast and cheap to deploy. Skills include query, detect, point, and caption, all native and all returning structured output.
Params
9.3 B
Context
—
Downloads 30d
10 K
Likes
91
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)10 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f8_e4m3 | 10.5 GB | 13.4 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.30
input / 1M
$2.50
output / 1M
—
cached input / 1M
$2.80
1M in + 1M out
- Context window
- 32,000 tokens
- Max output
- 4,096 tokens
- Providers
- 1
- Cheapest provider
- PrimeIntellect · $0.30 / $2.50
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✗ Tool calling
✓ Reasoning
✗ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Parameters
- 9.3 B
- Tensor type
- F8_E4M3
- Licence
- other
- First seen on the Hub
- 2026-06-30
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any image-text-to-text model