Hugging Face's logo
Erik Scholz's picture
31 28 331

Erik Scholz

Green-Sky
raincandy-u's profile picture l0d0v1c's profile picture russd's profile picture
·

AI & ML interests

None yet

Recent Activity

reacted to eaddario's post with 🚀 about 15 hours ago
Experimental global target bits‑per‑weight quantization of google/gemma-4-E2B-it, google/gemma-4-E4B-it and google/gemma-4-26B-A4B-it Unlike standard llama.cpp quantizations that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global file size target. Key Advantages: - VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM). - Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs. Full benchmarks (PPL, KLD, ARC, MMLU, etc.) and methodology in the models' cards https://huggingface.co/eaddario/gemma-4-E2B-it-GGUF https://huggingface.co/eaddario/gemma-4-E4B-it-GGUF https://huggingface.co/eaddario/gemma-4-26B-A4B-it-GGUF
liked a model 1 day ago
LuffyTheFox/Qwen3.6-35B-A3B-Plus-Uncensored-Wasserstein-GGUF
liked a model 1 day ago
stduhpf/Nucleus-Image-sdcpp
View all activity

Organizations

Social Post Explorers's profile picture