Unsloth releases MOSS-Image-Base-FP8 quantized text-to-image model on Hugging Face
unsloth · hf · 2026-10-22
Unsloth has released MOSS-Image-Base-FP8 on Hugging Face, a quantized (FP8) checkpoint of the MOSS text-to-image base model.
- Pipeline: text-to-image, works with diffusers and safetensors
- Formats: FP8/INT8 quantized, diffusion-single-file for ComfyUI-style workflows
A practical option for running MOSS image generation locally on memory-constrained GPUs.
More from Multimodal
- Suno Highlights Five Niche Features Most Users Don't Know About — suno · 2026-10-23
- Meshy offers Hermes users a month of Pro with API access for $1 — Teknium · 2026-10-23
- Customuse launches Smart Mesh AI with geometry-aware adaptive character clothing tool — SimplyAnnisa · 2026-10-23
- AI-generated movie poster 'The Chase' crams a wolf, a plane and muscle cars into one chase — Aggravating-Sir-115 · 2026-10-23
- SteerTTS-edge: an 11.84MB steerable TTS with unchanged WER running 19x realtime on CPU — Working_Hat5120 · 2026-10-23
- ElevenLabs' Chimera pairs Eleven v4 voice with Seedance video to make character images speak — AIwithGhotai · 2026-10-23