Measured peak <192 GB; estimated 256GB fit.
AI & ML interests
Fast local LLM inference and tested model releases for Apple Silicon and NVIDIA CUDA.
Recent Activity
View all activity
MLX models for 64GB Macs. See notes for measured versus estimated fit; context length and concurrent requests affect memory use.
-
TensorFold/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bit
Text Generation • 32B • Updated • 597 • 1 -
TensorFold/Qwen3.8-27B-MLX-4bit
Image-Text-to-Text • 27B • Updated • 1.8k • 1 -
TensorFold/Muse-Glimmer-30B-MLX-4bit
Image-Text-to-Text • 30B • Updated • 284 • 2 -
TensorFold/Nex-N2.5-mini-MLX-4bit
Image-Text-to-Text • 35B • Updated • 213
Measured peak <192 GB; estimated 256GB fit.
M3 Studio peaks below 96 GB; 32 GB nominal headroom on 128GB Macs. Estimated fit; start with short context.
MLX models for 64GB Macs. See notes for measured versus estimated fit; context length and concurrent requests affect memory use.
-
TensorFold/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bit
Text Generation • 32B • Updated • 597 • 1 -
TensorFold/Qwen3.8-27B-MLX-4bit
Image-Text-to-Text • 27B • Updated • 1.8k • 1 -
TensorFold/Muse-Glimmer-30B-MLX-4bit
Image-Text-to-Text • 30B • Updated • 284 • 2 -
TensorFold/Nex-N2.5-mini-MLX-4bit
Image-Text-to-Text • 35B • Updated • 213