Topic
local models
4 entries explored this theme.
July 29, 2026
Quantization quality cliffs: where 4-bit stops being good enough
July 23, 2026
MLX vs llama.cpp for local LLM inference on Apple Silicon in 2026
July 23, 2026
DeepSeek V4 vs Qwen 3.6 for local coding models in 2026
July 8, 2026
Local LLMs people actually run in 2026: Mac mini, consumer GPUs, and the frontier gap