view post Post 4359 You can now run Kimi K2 Thinking locally with our Dynamic 1-bit GGUFs: unsloth/Kimi-K2-Thinking-GGUFWe shrank the 1T model to 245GB (-62%) & retained ~85% of accuracy on Aider Polyglot. Run on >247GB RAM for fast inference.We also collaborated with the Moonshot AI Kimi team on a system prompt fix! 🥰Guide + fix details: https://docs.unsloth.ai/models/kimi-k2-thinking-how-to-run-locally See translation ❤️ 10 10 🚀 9 9 🔥 6 6 🤗 4 4 🤯 3 3 + Reply
Whisper ACFT Collection https://github.com/futo-org/whisper-acft • 6 items • Updated Jun 26, 2024 • 7
Running on Zero Featured 2.01k Chat With Janus-Pro-7B 🌍 2.01k A unified multimodal understanding and generation model.
lmstudio-community/DeepSeek-R1-Distill-Qwen-14B-GGUF Text Generation • 15B • Updated Jan 20 • 5.03k • 38