LocalClaw/LLM/Moondream 2
Open-weight local LLM

Moondream 2

Tiny vision model. Surprisingly good at describing images and OCR. Runs on anything.

Laptop ready 4 GB RAM fp16 Image description
Run with LocalClaw Compare all models
Parameters
1.9B
Minimum RAM
4 GB
Model size
1.9 GB
Quantization
fp16

Can Moondream 2 run locally?

Moondream 2 is a good fit for normal laptops and compact desktops with 8 GB RAM or more.

Search for moondream2 in LM Studio or another GGUF-compatible runtime.

vikhyatk/moondream2
visionlightspeed

Install path

01
Check RAM fitMinimum 4 GB RAM. Start with the fp16 quant.
02
Load the modelSearch moondream2 in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Strengths

  • Tiny vision model — runs on anything
  • Good OCR
  • Great for image captioning
  • Apache 2.0

Limitations

  • Very limited context
  • Weak at complex reasoning
  • English-only

Best use cases

  • Image description
  • OCR
  • Visual Q&A
  • Document scanning
  • Accessibility tools

Capability profile

speed
10
quality
4
coding
2
reasoning
3

Technical notes

Developer
Vikhyat Korrapati
License
Apache 2.0
Context window
2,048 tokens
Architecture
SigLIP vision encoder + Phi-1.5 language model

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Entry laptop fitMacBook Air 8GBMore headroomMac mini M4 16GBAll compatible picks8GB RAM guide

Similar models to compare

LLaVA 1.6 (7B) 7BMiniCPM-V (8B) 8BLLaVA-Phi3 (3.8B) 3.8B

Where to go next