ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration Paper β’ 2511.21689 β’ Published Nov 26, 2025 β’ 127
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8 Any-to-Any β’ 33B β’ Updated 9 days ago β’ 142k β’ 45
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 Any-to-Any β’ 33B β’ Updated 6 days ago β’ 238k β’ 287
view post Post 2823 Qwen3.6-35B-A3B can now be run locally! πThe model is the strongest mid-sized LLM on nearly all benchmarks.Run on 23GB RAM via Unsloth Dynamic GGUFs.GGUFs to run: unsloth/Qwen3.6-35B-A3B-GGUFGuide: https://unsloth.ai/docs/models/qwen3.6 See translation 13 replies Β· π 8 8 π₯ 7 7 π€ 1 1 + Reply