view post Post 8566 Qwen3-Next can now be Run locally! (30GB RAM)Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUFThe models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.π Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-nextThinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF See translation π₯ 37 37 β€οΈ 11 11 π 7 7 π€ 3 3 + Reply
omlab/omdet-turbo-swin-tiny-hf Zero-Shot Object Detection β’ 0.1B β’ Updated Dec 18, 2024 β’ 5.56k β’ 39
Less is More: Recursive Reasoning with Tiny Networks Paper β’ 2510.04871 β’ Published Oct 6, 2025 β’ 507
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain Paper β’ 2509.26507 β’ Published Sep 30, 2025 β’ 545
smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI Image-to-Text β’ 2B β’ Updated Sep 18, 2025 β’ 270 β’ 58