eaddario/imatrix-calibration
Viewer • Updated • 299 • 7.36k • 73
Ed Addario PRO
eaddario
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
updated a model 2 days ago
eaddario/IQ2_K-IQ6_K-Test-Models posted an update 2 days ago
Experimental global target bits‑per‑weight quantization of IFM/K2-Horizon-7B and IFM/K2-Horizon-MoVA-36B-A4B.
Unlike standard llama.cpp quantization that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach automatically optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global 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, GPQA, MMLU, etc.) and methodology in the model's card.
https://huggingface.co/eaddario/K2-Horizon-7B-GGUF
https://huggingface.co/eaddario/K2-Horizon-MoVA-36B-A4B-GGUF updated a model 2 days ago
eaddario/K2-Horizon-7B-GGUFOrganizations
