Ornith-1.5-122B-GGUF

Overview

Ornith's 122B flagship at Unsloth's Dynamic 4-bit - SWE-bench Pro 76.9 and Terminal-Bench 2.1 at 81.2, ahead of Qwen3.8-Flash-Next nearly everywhere. An 80 GB llama.cpp download for 96 GB+ setups.

Good for

• agentic
• chat
• coding

Recommended hardware

≈ 96 GB VRAM to run this 122B model at the UD-Q4_K_XL quantization.

Needs 128 GB+ of VRAM or unified memory (e.g. multi-GPU with 2x 96 GB cards, or a 128 GB Mac)

Links

• View on HuggingFace
• Run on Infersec