ByteShape

AI & ML interests

Accelerating AI by Learning Optimal Bitlengths

Recent Activity

Ali93H  new activity 1 day ago

byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF:is it supposed to run this slow on a broadwell xeon?

Ali93H  new activity 1 day ago

byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF:Maybe it is not the Instruct-2507 model?

Ali93H  new activity 1 day ago

byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF:I use this quantized model for RAG, if context is long, always get empty output

View all activity

Team members 4