Kosh's picture

6 17

Kosh

Kosh69

·

AI & ML interests

None yet

Recent Activity

reacted to mitkox's post with 🚀 about 15 hours ago

I run Qwen3-Coder 480B locally on my Z8, with a 1-million token context window. It’s the equivalent of parallel-parking a Nimitz-class carrier in a kiddie pool. Thanks to whatever dark pact the llama.cpp, CUDA, and kernel folks signed, hybrid inferencing + VRAM↔RAM offload let me stream the model’s synapses across Xeon, RAM, and four lonely A6000s without summoning either the OOM killer or a small house fire.

liked a model 2 days ago

mradermacher/KAT-V1-40B-GGUF

reacted to AdinaY's post with 👍 2 days ago

KAT-V1 🔥 a LLM that tackles overthinking by switching between reasoning and direct answers, by Kuaishou. https://huggingface.co/Kwaipilot/KAT-V1-40B ✨ 40B ✨ Step-SRPO: smarter reasoning control via RL ✨ MTP + Distillation: efficient training, lower cost

View all activity

Organizations

None yet

models 0

None public yet

datasets 0

None public yet