MLX fine-tuning toolkit for Mac Studio M3 Ultra 512 GB — distill Claude Opus reasoning into Mistral Large 123B for the ailiance LLM stack.
-
Updated
May 21, 2026 - Python
MLX fine-tuning toolkit for Mac Studio M3 Ultra 512 GB — distill Claude Opus reasoning into Mistral Large 123B for the ailiance LLM stack.
ailiance fine-tuning pipeline — model training, evaluation, registry (Unsloth, LoRA).
Benchmarking MLX pour modèles open-source et fine-tunes Ailiance (gsm8k, arc, mmlu_pro, perplexité 5 niches)
Frontend cockpit for ailiance.fr LLM fleet — public showcase + Tailscale-only admin (FastAPI + Vite + React 19)
To associate your repository with the ailiance topic, visit your repo's landing page and select "manage topics."