Youssofal/Qwen3.8-Flash-Next-MTPLX-Bare-Speed Text Generation • 126B • Updated about 22 hours ago • 4.33k • 7
macmacmacmac/Qwen3.8-Flash-Next-MLX-4bit-MTP Image-Text-to-Text • 29B • Updated 21 days ago • 146 • 1
macmacmacmac/Qwen3.8-Flash-Next-MLX-4bit-MTP Image-Text-to-Text • 29B • Updated 21 days ago • 146 • 1
macmacmacmac/Qwen3.8-Flash-Next-MLX-4bit-MTP Image-Text-to-Text • 29B • Updated 21 days ago • 146 • 1
Running VibeThinker WebGPU Train + Hot-Swap LoRA 🔥 In-browser WebGPU LoRA training + hot-swap (VibeThinker-3B)
Running VibeThinker WebGPU Train + Hot-Swap LoRA 🔥 In-browser WebGPU LoRA training + hot-swap (VibeThinker-3B)