Running on Zero MCP Featured 54 BitDance-14B-64x 🚀 54 Open-source autoregressive model with binary visual tokens.
view post Post 5131 We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe See translation 1 reply · 🔥 29 29 🤗 5 5 + Reply
Unsloth Dynamic 2.0 Quants Collection New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 73 items • Updated 8 days ago • 373