⚡ 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 Qwen AgentWorld 35B A3B — APEX GGUF APEX (Adaptive Precision for EXpert Models) quantizations of Qwen/Qwen AgentWorld 35B A3B — a world model / agent environment simulation MoE built on Qwen3.5 35B A3B Base. Brought to you by the LocalAI team APEX Project Technical Report Available Files File Profile Best For Qwen AgentWorld 35B A3B APEX I Balanced.gguf I Balanced Best overall — imatrix enhanced Qwen AgentWorld 35B A3B APEX I Quality.gguf I Quality Highest quality with imatrix Qwen AgentWorld 35B A3B APEX Quality.gguf Quality Highest quality (no imatrix) Qwen AgentWorld 35B A3B APEX Balanced.gguf Balanced General purpose Qwen AgentWorld 35B A3B APEX I Compact.gguf I Compact Consumer GPUs, imatrix enhanced Qwen Age…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy