The Local LLM Index / Quantization & Formats / #96
jjang-ai/jangq
by jjang-ai · Quantization & Formats · updated 1d ago
JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon
60
momentum
184
stars
23
forks
#96
rank
apple-siliconggufjang-quantizationllamacppllmmlxmlxllmomlxomlx-alternativequantization
View on GitHub →