Tiny Models These can run on a NVIDIA GeForce MX150 at a relatively fast performance, load in FP16 if they aren't already BF16 or FP16 Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8 Text Generation • 0.5B • Updated Oct 9, 2024 • 650 • 10 vicgalle/gpt2-open-instruct-v1 Text Generation • 0.1B • Updated Apr 12, 2023 • 491 • 37 unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF Text Generation • 2B • Updated Apr 19, 2025 • 42.9k • 152
unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF Text Generation • 2B • Updated Apr 19, 2025 • 42.9k • 152
Favorite Models🌟 Models that i like ByteDance/Hyper-SD Text-to-Image • Updated Dec 5, 2024 • 45.1k • • 1.35k microsoft/Phi-3.5-mini-instruct Text Generation • 4B • Updated Dec 10, 2025 • 1.07M • 1.06k
Tiny Models These can run on a NVIDIA GeForce MX150 at a relatively fast performance, load in FP16 if they aren't already BF16 or FP16 Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8 Text Generation • 0.5B • Updated Oct 9, 2024 • 650 • 10 vicgalle/gpt2-open-instruct-v1 Text Generation • 0.1B • Updated Apr 12, 2023 • 491 • 37 unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF Text Generation • 2B • Updated Apr 19, 2025 • 42.9k • 152
unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF Text Generation • 2B • Updated Apr 19, 2025 • 42.9k • 152
Favorite Models🌟 Models that i like ByteDance/Hyper-SD Text-to-Image • Updated Dec 5, 2024 • 45.1k • • 1.35k microsoft/Phi-3.5-mini-instruct Text Generation • 4B • Updated Dec 10, 2025 • 1.07M • 1.06k
