Unsloth's dynamic GGUF quants shrink Ornith-1.5-122B to a 40GB file
Unsloth released dynamic GGUF quantizations of Ornith-1.5-122B, compressing the MoE reasoning and coding model to a 40GB file that fits on a single 48GB GPU.
Read the full story at AlphaSignal ↗
Timeline · 1 report
- 2026-11-17 22:00 · AlphaSignal
Unsloth Shrinks Ornith-1.5-122B to Fit on a Single 48GB GPU