MODEL CATALOG
One model. Full disclosure.
One disclosed text model, with a pinned community artifact, known hardware, and explicit capability limits.
Private beta · text only
qwen3.8-27b-abliterated
AWQ INT4 · NVIDIA RTX 3090 Ti · 8,192 total tokens · 4,096 maximum completion.
Non-thinking by default. Text and SSE streaming; tools, images, audio, and thinking requests are not release-supported.
Qwen model family; community build by twolven. Independently served by AblitAI, with no affiliation or endorsement by Alibaba or Qwen.
Read the model card ↗Choose by the current envelope
Base-model capabilities and repository names do not automatically describe this endpoint. Read the client support matrix, the text quickstart, and current pack pricing before integrating. Live status reports availability separately from the model specification.