These can run on a NVIDIA GeForce MX150 at a relatively fast performance, load in FP16 if they aren't already BF16 or FP16
Caio Silva De Oliveira
CaioXapelaum
AI & ML interests
None yet
Organizations
None yet
models 12
CaioXapelaum/Qwen-2.5-0.5B-Instruct-4bit
Text Generation • 0.5B • Updated
• 1 • 2
CaioXapelaum/Qwen2.5-1.5B-Instruct-Q4-mlx
Text Generation • 0.2B • Updated
• 29
CaioXapelaum/tiny_starcoder_py-Q8_0-GGUF
Text Generation • 0.2B • Updated
• 15
CaioXapelaum/Qwen2.5-3B-F32-GGUF
Updated
CaioXapelaum/sdxl
Text-to-Image • Updated
• 68 • 1
CaioXapelaum/Qwen2.5-Coder-0.5B-Instruct-Q4-mlx
Text Generation • 77.3M • Updated
• 4
CaioXapelaum/Qwen2.5-Coder-1.5B-Q4_K_M-GGUF
Text Generation • 2B • Updated
• 20
CaioXapelaum/entity-classifier
Image Classification • 85.8M • Updated
• 7
CaioXapelaum/Llama-3.1-Storm-8B-Q5_K_M-GGUF
Text Generation • 8B • Updated
• 16
CaioXapelaum/Orca-2-7b-Patent-Instruct-Llama-2-Q5_K_M-GGUF
7B • Updated
• 5