The Local LLM Index / Quantization & Formats / #106

jjang-ai/jangq

by jjang-ai · Quantization & Formats · updated today

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

58
momentum
217
stars
27
forks
#106
rank
apple-siliconggufjang-quantizationllamacppllmmlxmlxllmomlxomlx-alternativequantization
View on GitHub →