JThomas-CoE/coe-gemma4-psychology-mmlu_pro-14b-a4b-q4
https://huggingface.co/JThomas-CoE/coe-gemma4-psychology-mmlu_pro-14b-a4b-q4Base model: google/gemma-4-26b-it Architecture: MoE — 26B total / ≈4B active parameters (1 shared expert + 8 routed from a pool of 128 per MoE layer, 30 MoE layers) Method: Activation-directed expert surgery — 128 → 64 experts per layer (50% reduction) Quantization: Q4KM (≈9.7 GB on disk) Tags:…
Sourced from
- HuggingFace — JThomas-CoE/coe-gemma4-psychology-mmlu_pro-14b-a4b-q4
Related resources
Base model: google/gemma-4-26b-it Architecture: MoE — 26B total / ≈4B active parameters (1 shared expert + 8 routed from a pool of 128 per MoE layer, 30 MoE layers) Method: Activation-directed expert surgery — 128 → 64 experts per layer (50% reduction) Quantization: Q4KM (≈9.7 GB on disk) Tags:…
Base model: google/gemma-4-26b-it Architecture: MoE — 26B total / ≈4B active parameters (1 shared expert + 8 routed from a pool of 128 per MoE layer, 30 MoE layers) Method: Activation-directed expert surgery — 128 → 64 experts per layer (50% reduction) Quantization: Q4KM (≈9.7 GB on disk) Tags:…
Junhauwong/Surge-Cognition-4x8B
by JunhauwongFrom Inquiry to Decision: Building Trustworthy Medical AI