Erik Scholz's picture

Erik Scholz

Green-Sky

·

Green-Sky

AI & ML interests

None yet

Recent Activity

repliedto eaddario's post 23 minutes ago

Experimental global target bits‑per‑weight quantization of Qwen/Qwen3.5-4B and Qwen/Qwen3.5-9B 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/Qwen3.5-4B-GGUF https://huggingface.co/eaddario/Qwen3.5-9B-GGUF

reacted to eaddario's post with 👍 28 minutes ago

Experimental global target bits‑per‑weight quantization of Qwen/Qwen3.5-4B and Qwen/Qwen3.5-9B 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/Qwen3.5-4B-GGUF https://huggingface.co/eaddario/Qwen3.5-9B-GGUF

new activity about 11 hours ago

AuriAetherwiing/TQ3.5-27B-Musica-v1:Does TQ refer to 'turboquant'?

View all activity

Organizations

Green-Sky 's Spaces 1

Sd.cpp

stable-diffusion.cpp in server mode