nthngdy/Llama-3.1-8B-Instruct_qfilt
32.8k • Updated • 1.75k
Q-Filters
Pre-computed Q-Filters for efficient KV cache compression.
-
-
nthngdy/Llama-3.2-1B-Instruct_qfilt
8.19k • Updated • 1.49k -
nthngdy/Llama-3.2-3B-Instruct_qfilt
28.7k • Updated • 8.25k -
nthngdy/Llama-3.2-3B_qfilt
28.7k • Updated • 1.41k -
nthngdy/Llama-3.1-8B_qfilt
32.8k • Updated • 1.41k -
nthngdy/Llama-3.1-70B-Instruct_qfilt
81.9k • Updated • 1.4k -
nthngdy/Llama-3.1-70B_qfilt
81.9k • Updated • 1.4k -
nthngdy/Meta-Llama-3.1-405B_qfilt
258k • Updated • 1.4k -
nthngdy/Mistral-Small-24B-Instruct-2501_qfilt
41k • Updated • 1.45k -
nthngdy/phi-4_qfilt
51.2k • Updated • 1.39k -
nthngdy/Llama-3.2-1B_qfilt
8.19k • Updated • 1.47k -
nthngdy/Qwen2.5-7B_qfilt
14.3k • Updated • 1.4k -
nthngdy/Qwen2.5-7B-Instruct_qfilt
14.3k • Updated • 1.39k -
nthngdy/DeepSeek-R1-Distill-Llama-8B_qfilt
32.8k • Updated • 1.36k -
nthngdy/DeepSeek-R1-Distill-Qwen-1.5B_qfilt
7.17k • Updated • 1.38k