Open source multimodal decision model XOR launches on Hugging Face, 260k context, Qwen-based
TheMoonMidas · x · 2026-09-24
XyneAI introduced XOR, an open source multimodal "Jev-like" decision model now live on Hugging Face (juspay/xor).
- Multimodal: built for text + visual classification
- 260k token context window
- Based on Qwen3.6, with data sovereignty and enterprise-grade use in mind
Weights and configs are public, and the chat template supports image and video inputs.
More from Models
- Open-weight model Jev hosts first SF hack/demo night with dumpling bar this Friday — Aizkmusic · 2026-09-24
- Frontier labs' health week: Opus 5.5 cut 40%, 950 agents find new enzyme — HealthcareAIGuy · 2026-09-24
- Monologue launches in-house dictation model mono-1: 55% fewer edits, 3x faster than API pipeline — every · 2026-09-24
- Anthropic cut Opus 5.5 prices, then broke four things your agent depends on — rseroter · 2026-09-24
- ChatGPT Voice with tools and MCP impresses: interruptible, pulls local Mac files — athyuttamre · 2026-09-24
- Set max_tokens to 1 and Read Logprobs: Turn Any Hosted LLM Into a Classifier — keep_up_sharma · 2026-09-24