Otilde/Ministral-3-3B-Instruct-2512-Q7-MLX-Dynamic
Text Generation • 0.9B • Updated • 21
Ɵtilde
Otilde
AI & ML interests
My goal is to provide high quality model quantizations and fine-tunes (Apple Silicon–optimized) to boost productivity across tech niches. I maintain recommended models and accept requests.
Organizations
Otilde/Orchestrator-8B-MLX-F32
Text Generation • 8B • Updated • 6
Otilde/Ministral-3-3B-Instruct-2512-MLX-F32
Text Generation • 3B • Updated • 19
Otilde/Qwen3-4B-Instruct-2507-MLX-Dynamic-5bit
Text Generation • 0.7B • Updated • 7
Otilde/SmolLM-135M-Dynamic-Q5-MLX
Text Generation • 21.1M • Updated • 2
Otilde/Seed-OSS-36B-Instruct-Mixed_4_6-MLX
Text Generation • 36B • Updated • 11
Otilde/granite-4.0-micro-llamafile
Updated • 30
Otilde/Qwen3Guard-Gen-4B-Heretic-MLX-Q8
Text Generation • 1B • Updated • 30
Otilde/Qwen3Guard-Gen-4B-Heretic
Text Generation • 4B • Updated • 1
Otilde/Qwen3Guard-Gen-4B-MLX-Q8
Text Generation • 1B • Updated • 9
Otilde/Anonymizer-4B-F32-MLX
Text Generation • 1B • Updated • 5
Otilde/syngen-reasoning-0.6b-MLX-F32
Text Generation • 0.2B • Updated • 3
Otilde/gpt-oss-safeguard-20b-MXFP4-Q4-MLX
Text Generation • 21B • Updated • 45
Otilde/UserLM-8b-MLX-Mixed-4_6
Text Generation • 8B • Updated • 1
Otilde/Distil-PII-Llama-3.2-3B-Instruct-mxfp4-MLX
Text Generation • 3B • Updated • 37
Otilde/Schematron-3B-mxfp4-F32-MLX
Text Generation • 3B • Updated • 9
Otilde/CheapResearch-4B-Thinking-MXFP4-MLX
Text Generation • 4B • Updated • 1
Otilde/DeepHat-V1-7B-Q8-MLX
Text Generation • 8B • Updated • 87
Otilde/SmolLM3-3B-Base-Q8-MLX
Text Generation • 0.9B • Updated • 9
Otilde/GRMR-V3-G4B-8bit-MLX
Text Generation • 1B • Updated • 55 • 1