Files
ik_llama.cpp/ggml
Iwan Kawrakow 0b9177bb11 iq3_k: Metal dot product
Quite slow: 43 t/s for a 7B model
2024-07-31 08:44:19 +02:00
..
2024-07-27 07:55:01 +02:00
2024-07-30 16:11:25 +03:00
2024-07-31 08:44:19 +02:00
2024-07-27 07:55:01 +02:00
2024-07-27 07:55:01 +02:00