hello hazime

hellohazime

·

AI & ML interests

None yet

Recent Activity

new activity 18 days ago

Qwen/Qwen3.8-Flash-Next-FP8:FP8 config: modules_to_not_convert paths never match on text-only loads (silent quality issue) + fp8 PLE table lacks a dequant path

updated a model 30 days ago

hellohazime/Kimi-K3-REAP-512GB-GGUF

updated a model about 1 month ago

hellohazime/Kimi-K3-REAP640ja-IQ1_S-GGUF

View all activity

Organizations

None yet

hellohazime 's models 7

hellohazime/Kimi-K3-REAP-512GB-GGUF

Text Generation • 1.8T • Updated 30 days ago • 1.26k • 15

hellohazime/Qwen3.8-2.4T-A95B-REAP-512GB-GGUF

Text Generation • 1.5T • Updated Aug 16 • 1.72k

hellohazime/Qwen3.8-2.4T-A95B-REAP-256GB-GGUF

Text Generation • 1.1T • Updated Aug 16 • 32.2k • 3

hellohazime/Kimi-K3-REAP640ja-IQ1_S-GGUF

Text Generation • 2T • Updated Aug 16 • 139

hellohazime/qwen35-2b-openclaw-termux-stage1

Image-Text-to-Text • 2B • Updated Mar 28 • 9 • 1

hellohazime/qwen3-1p7b-pokellm-lora_50k_ev0p05

Text Generation • Updated Sep 11, 2025 • 17

hellohazime/qwen3-1p7b-pokellm-lora

Text Generation • Updated Sep 9, 2025 • 19