eaddario/Qwen3-30B-A3B-GGUF
Text Generation • 31B • Updated • 763 • 4
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 about 21 hours ago
eaddario/IQ2_K-IQ6_K-Test-Models posted an update 1 day 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 1 day ago
eaddario/K2-Horizon-7B-GGUFOrganizations
eaddario/Qwen3-30B-A3B-pruned-GGUF
Text Generation • 29B • Updated • 630 • 4
eaddario/Dolphin-Mistral-24B-Venice-Edition-GGUF
Text Generation • 24B • Updated • 2.91k • 7
eaddario/Dolphin-Mistral-24B-Venice-Edition-pruned-GGUF
Text Generation • 24B • Updated • 747 • 1
eaddario/Dolphin3.0-R1-Mistral-24B-GGUF
Text Generation • 24B • Updated • 1.63k • 2
eaddario/Dolphin3.0-Mistral-24B-GGUF
Text Generation • 24B • Updated • 2.41k • 2
eaddario/OLMo-2-1124-7B-Instruct-GGUF
Text Generation • 7B • Updated • 289
eaddario/Qwen3-8B-GGUF
Text Generation • 8B • Updated • 632 • 1
eaddario/Llama-xLAM-2-8b-fc-r-GGUF
Text Generation • 8B • Updated • 274 • 1
eaddario/Llama-Guard-3-8B-GGUF
Text Generation • 8B • Updated • 937
eaddario/Watt-Tool-8B-GGUF
Text Generation • 8B • Updated • 1.26k • 6
eaddario/DeepSeek-R1-Distill-Qwen-7B-GGUF
Text Generation • 8B • Updated • 1.11k • 3
eaddario/Hammer2.1-7b-GGUF
Text Generation • 8B • Updated • 820 • 2
eaddario/DeepSeek-R1-Distill-Llama-8B-GGUF
Text Generation • 8B • Updated • 625 • 1