Hugging Face's logo
Anthony Mikinka's picture

Anthony Mikinka

anthonymikinka
8 88 611
marco4kpro1's profile picture nmbtw's profile picture ginigen-ai's profile picture
·
https://anthonymikinka.com

AI & ML interests

ANE Focused

Recent Activity

liked a model about 20 hours ago
abenzerps/Qwen-Image-2.1-Uncensored-GGUF
reacted to harshitkgupta's post with 🚀 about 20 hours ago
Fine-tuned Qwen 2.5 (0.5B → 3B) on real coding-agent traces, 10 controlled runs, one 16GB Mac. Compared PyTorch MPS vs. Apple MLX for local LoRA SFT — and the honest answer is "it depends on what you're optimizing for": • PyTorch MPS: 2.2x–5.7x faster raw throughput, but hits a hard memory wall — can't load a 3B model in FP16 on 16GB. • Apple MLX: 4-bit QLoRA fits 3B+ models with almost flat memory scaling as context grows (+109 MB going from 1k→4k tokens). • 4-bit quantization doesn't cost you convergence — eval loss tracks closely across backends. • The bigger surprise: most of MLX's slowdown isn't the 4-bit dequant tax. Two of the 10 runs went unquantized to isolate it — dequant only explains 1.07x–1.4x of the gap. A ~4.1–4.6x framework-level gap remains either way. All 10 LoRA adapters + Trackio logs are public so the numbers are checkable, not just claimed. Full writeup: https://huggingface.co/blog/harshitkgupta/fine-tuning-coding-agents-on-mac-pytorch-mps-mlx
liked a model about 21 hours ago
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF
View all activity

Organizations

None yet