I host 25+ 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.
APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient — edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).
The key insight: in MoE models, expert FFN tensors make up the bulk of model weight but only ~8/256 experts activate per token. APEX compresses middle-layer experts more aggressively while preserving edge layers (first/last 5) and keeping attention, SSM/Mamba, and shared expert tensors at higher precision.
See the APEX project for full details, technical report, and scripts.
Architecture
Model: Qwen3.6 35B-A3B Claude 4.6 Opus Reasoning Distilled (reasoning fine-tune)
Base: Qwen 3.6 35B-A3B
Layers: 40
Experts: 256 routed + shared (8 active per token)
Total Parameters: ~35B
Active Parameters: ~3B per token
Attention: Hybrid (full attention every 4th layer, linear/Mamba otherwise)
Modality: Text only (no vision encoder in upstream)
APEX Config: 5+5 symmetric edge gradient across 40 layers
Calibration: v1.3 diverse dataset (chat, code, reasoning, multilingual, tool-calling, Wikipedia)
Run with LocalAI
local-ai run mudler/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-GGUF@Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-I-Balanced.gguf
