Small Models ( 8B max ) GTX 1660 Super Must run at Quant 4 or higher, 15tps or higher. Full Precision vs Quant not benchmarked. MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF Text Generation • 8B • Updated Dec 6, 2025 • 57.5k • 4 unsloth/Qwen3-4B-Instruct-2507-GGUF 4B • Updated Aug 20, 2025 • 55.2k • 132 unsloth/SmolLM3-3B-128K-GGUF 3B • Updated Jul 8, 2025 • 7.1k • 36
MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF Text Generation • 8B • Updated Dec 6, 2025 • 57.5k • 4
Small Models ( 8B max ) GTX 1660 Super Must run at Quant 4 or higher, 15tps or higher. Full Precision vs Quant not benchmarked. MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF Text Generation • 8B • Updated Dec 6, 2025 • 57.5k • 4 unsloth/Qwen3-4B-Instruct-2507-GGUF 4B • Updated Aug 20, 2025 • 55.2k • 132 unsloth/SmolLM3-3B-128K-GGUF 3B • Updated Jul 8, 2025 • 7.1k • 36
MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF Text Generation • 8B • Updated Dec 6, 2025 • 57.5k • 4