Hugging Face's logo
Ruslan's picture
13 1 57

Ruslan

uzvisa
cnrkaya's profile picture Hastagaras's profile picture gaytri1111's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago
baidu/Unlimited-OCR
new activity about 2 months ago
Qwen/Qwen3.6-35B-A3B:how to enable non-thinking mode of this model in llama.cpp?
reacted to eaddario's post with 👍 about 2 months ago
Experimental global target bits‑per‑weight quantization of Qwen/Qwen3.6-27B and Qwen/Qwen3.6-35B-A3B. 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, GPQA, MMLU, etc.) and methodology in the models' cards. https://huggingface.co/eaddario/Qwen3.6-27B-GGUF https://huggingface.co/eaddario/Qwen3.6-35B-A3B-GGUF
View all activity

Organizations

None yet