v0.38.0 — Vision/Multimodal Support
Vision/Multimodal Support
Models with vision capability now automatically get their multimodal projector (mmproj) downloaded and launched with --mmproj.
New
- Vision support: Catalog models can declare an mmproj file. Download fetches it alongside the model. llama-server launches with
--mmprojautomatically. - 3 new vision models: Qwen3.5-0.8B, 4B, 9B (all vision-native)
- Qwen3.5-27B tagged as vision-capable with mmproj
- UI image attach: Button appears for vision-capable models. Attach images, see previews, send with messages.
- 👁 badge: Vision models marked in model dropdown and dashboard
/v1/modelscapabilities: Returns["text", "vision"]for vision models/api/statusvision field:vision: true/falseper model
Changed
- Mini swapped from Qwen3-8B to Qwen3.5-9B (same size, gains vision)
- Fly API app (
mesh-llm-api) retired — console serves both UI and API
Mesh
- 3 hosts: Mini (Qwen3.5-9B 👁), Studio (MiniMax-M2.5), James (Qwen2.5-72B)
- Console: https://www.mesh-llm.com/chat