Unsloth ships 44.5GB quants of Ornith-1.5-122B, 82% smaller with ~84% accuracy
danielhanchen · x · 2026-10-21
Unsloth released UD dynamic quantized GGUFs for Ornith's new 122B model. The UD-Q2KXL quant is just 44.5GB versus 249GB at BF16 (82% smaller) while retaining roughly 84% top-1 accuracy on wikitext general tasks and 89% on chat. A full benchmark curve across quant levels (IQ1M through Q80) is included for picking a tier by VRAM budget.
Related event: Unsloth Releases Quantized GGUF of Ornith-1.5-122B(2 posts)→
More from Models
- AI researcher: Claude finally finished tedious research tasks I gave up on years ago — MikePFrank · 2026-10-23
- Dream Labs emerges from stealth with Dream-1 robot foundation model at $3/hour — scott_e_reed · 2026-10-23
- Claude Models on Google Cloud (Anthropic managed) is now generally available — claudeai · 2026-10-23
- Beam vs GLM 5.3 Abliterated: 10-round attack/defense test shows 96% of vulns patched — bigblueboo · 2026-10-23
- ChatGPT web can actually listen to audio, but the same model can't via API or Codex — Possible_Statement84 · 2026-10-23
- MiniMax M3.1 Flash free for 3 days on 0G, with 1M context and 512K output — MiniMax_AI · 2026-10-23