bary

bpool

·

AI & ML interests

None yet

Recent Activity

updated a collection 2 days ago

updated a collection 2 days ago

new activity 3 days ago

XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B:GGUF/llama.cpp results: YaRN 512K works: 40/40 needle retrieval at 512K, zero short-task quality loss, ~660 tok/s prefill (llama.cpp, RX 7900 XTX)

View all activity

Organizations

None yet

Collections 13

View 13 collections

models 2

bpool/Qwen3-1.7B-openvino

Text Generation • Updated Dec 28, 2025 • 16 • 1

bpool/Qwen3-4B-Thinking-2507-openvino

Text Generation • Updated Sep 4, 2025 • 21

datasets 0

None public yet