Ornith 1.0 35B AEON Ultimate Uncensored GGUF GGUF quantizations of AEON 7/Ornith 1.0 35B AEON Ultimate Uncensored BF16, produced from the BF16 source weights using importance matrix calibration. Two variants are provided: standard trunk (no MTP) and MTP grafted (with Multi Token Prediction block for speculative decoding). Files Standard Trunk (no MTP) For standard autoregressive inference. Smaller files, no speculative decoding overhead. File Quant Size BPW Target GPU ornith aeon 35b Q8 0.gguf Q8 0 35 GB ~8.5 48GB+ (near lossless) ornith aeon 35b Q6 K.gguf Q6 K 27 GB ~6.6 32GB+ (high quality) ornith aeon 35b Q5 K M.gguf Q5 K M 24 GB ~5.7 24GB (quality first) ornith aeon 35b Q4 K M.gguf Q4 K M 21.2 GB ~4.8 24GB (balanced) ornith aeon 35b Q4 K S.gguf Q4 K S 19.9 GB ~4.6 24GB fallback ornith aeon 35b IQ4 XS.gguf IQ4 XS 18.7 GB ~4.3 20GB (RTX 4000 Ada) ornith aeon 35b Q3 K M.gguf Q3 K M 16.8 GB ~3.9 16GB GPUs ornith aeon 35b Q2 K.gguf Q2 K 12.9 GB ~3.0 12GB GPUs ornith aeon 35b IQ1 M.gguf IQ1 M 8.2 GB ~1.8 8GB GPUs ornith aeon 35b.imatrix 184 MB Importance matrix MTP Grafted (with Multi Token Prediction) These GGUFs contain all 785 MTP tensors grafted from the base Qwen/Qwen3.5 35B A3B…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy