Osmium

llava:13b

LLaVA 13B on your own machine

The classic local vision model. Short context, and weak at text-only coding.

Pull it

ollama pull llava:13b

Then pick it in Osmium under Settings → Local models. Nothing else to configure.

Parameters
13B
VRAM (4-bit)
10 GB
Disk
~7.5 GB
Context
4K tokens
Tool calling
No
Reads images
Yes
Generates images
No
Coding
3/10
Explaining
5/10

Scores are our own product guidance, not benchmark results.

Which hardware runs it

Checked against GPU memory. Osmium runs the same check on your real machine and also looks at system RAM and free disk. Unified-memory Macs need more headroom because the GPU shares one pool with the operating system.

  • 4 GB — GTX 1650 / MX570Needs 10 GB; this tier has 4 GB.Too big
  • 6 GB — RTX 2060 / 3050Needs 10 GB; this tier has 6 GB.Too big
  • 8 GB — RTX 3060 Ti / 4060Needs 10 GB; this tier has 8 GB.Too big
  • 12 GB — RTX 3060 / 4070Runs comfortably on 12 GB.Fits
  • 16 GB — RTX 4060 Ti / 4080Runs comfortably on 16 GB.Fits
  • 24 GB — RTX 3090 / 4090Runs comfortably on 24 GB.Fits
  • Mac 16 GB unifiedRuns comfortably on 16 GB.Fits
  • Mac 24 GB unifiedRuns comfortably on 24 GB.Fits
  • Mac 36 GB unifiedRuns comfortably on 36 GB.Fits
  • Mac 64 GB unifiedRuns comfortably on 64 GB.Fits

Other vision models