⚡ Each donation = another big MoE quantized I host 30+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory) — enough for ~30 50B class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20 100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. 🎉 Patreon (Monthly) ☕ Buy Me a Coffee ⭐ GitHub Sponsors Ornith 1.0 35B — APEX GGUF APEX (Adaptive Precision for EXpert Models) quantizations of deepreinforce ai/Ornith 1.0 35B — the lightweight, single GPU member of the Ornith 1.0 self improving family of open source agentic coding models (Qwen3.5 MoE base). Brought to you by the LocalAI team APEX Project Technical Report Available Files File Profile Best For Ornith 1.0 35B APEX I Balanced.gguf I Balanced Best overall — imatrix enhanced, lowest worst case divergence Ornith 1.0 35B APEX I Quality.gguf I Quality Highest quality with imatrix Ornith 1.0 35B APEX Quality.gguf Quality Highest quality (no imatrix) Ornith 1.0 35B APEX Balanced.gguf Balanced General purpose Ornith 1.0 35B APEX I Compact.gguf I Compact Consumer…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy