Hugging Face's logo
Ed Addario's picture
Building on HF
9 5 8

Ed Addario PRO

eaddario
Mdubbya's profile picture SaraRKO's profile picture John6666's profile picture
·

AI & ML interests

Finding ways to optimize LLMs' inference performance in resource-constrained environments (e.g. commodity hardware, desktops, laptops, mobiles, edge devices, etc.)

Recent Activity

posted an update 2 days ago
Experimental global target bits‑per‑weight quantization of mistralai/Ministral-3-14B-Instruct-2512 and mistralai/Ministral-3-14B-Reasoning-2512 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/Ministral-3-14B-Instruct-2512-GGUF https://huggingface.co/eaddario/Ministral-3-14B-Reasoning-2512-GGUF
updated a model 2 days ago
eaddario/Ministral-3-14B-Instruct-2512-GGUF
updated a model 2 days ago
eaddario/Ministral-3-14B-Reasoning-2512-GGUF
View all activity

Organizations

Hugging Face Discord Community's profile picture