sy128/CQ3-Qwen3-4B-K16-SqueezeLLM
4B • Updated • 40
CQ3-Baseline
-
-
sy128/CQ3-Qwen3-4B-K8-SqueezeLLM
4B • Updated • 48 -
sy128/CQ3-Qwen3-4B-K4-SqueezeLLM
4B • Updated • 40 -
sy128/CQ3-Qwen3-8B-K16-SqueezeLLM
8B • Updated • 37 -
sy128/CQ3-Qwen3-8B-K8-SqueezeLLM
8B • Updated • 35 -
sy128/CQ3-Qwen3-8B-K4-SqueezeLLM
8B • Updated • 34 -
sy128/CQ3-Qwen3-14B-K16-SqueezeLLM
15B • Updated • 42 -
sy128/CQ3-Qwen3-14B-K8-SqueezeLLM
15B • Updated • 31 -
sy128/CQ3-Qwen3-14B-K4-SqueezeLLM
15B • Updated • 35 -
sy128/CQ3-Qwen3-32B-K16-SqueezeLLM
33B • Updated • 20 -
sy128/CQ3-Qwen3-32B-K8-SqueezeLLM
33B • Updated • 25 -
sy128/CQ3-Qwen3-32B-K4-SqueezeLLM
33B • Updated • 35 -
sy128/CQ3-Qwen3-4B-K16-CodeQuant
4B • Updated • 30 -
sy128/CQ3-Qwen3-4B-K8-CodeQuant
4B • Updated • 23 -
sy128/CQ3-Qwen3-4B-K4-CodeQuant
4B • Updated • 26 -
sy128/CQ3-Qwen3-8B-K16-CodeQuant
8B • Updated • 32 -
sy128/CQ3-Qwen3-8B-K8-CodeQuant
8B • Updated • 18 -
sy128/CQ3-Qwen3-8B-K4-CodeQuant
8B • Updated • 22 -
sy128/CQ3-Qwen3-14B-K16-CodeQuant
15B • Updated • 19 -
sy128/CQ3-Qwen3-14B-K8-CodeQuant
15B • Updated • 24 -
sy128/CQ3-Qwen3-14B-K4-CodeQuant
15B • Updated • 32 -
sy128/CQ3-Qwen3-32B-K16-CodeQuant
33B • Updated • 24 -
sy128/CQ3-Qwen3-32B-K8-CodeQuant
33B • Updated • 18 -
sy128/CQ3-Qwen3-32B-K4-CodeQuant
33B • Updated • 14 -
sy128/CQ3-Qwen3-4B-W4-ParoQuant-WO
4B • Updated • 21 -
sy128/CQ3-Qwen3-4B-W3-ParoQuant-WO
4B • Updated • 17 -
sy128/CQ3-Qwen3-4B-W2-ParoQuant-WO
4B • Updated • 21 -
sy128/CQ3-Qwen3-8B-W4-ParoQuant-WO
8B • Updated • 25 -
sy128/CQ3-Qwen3-8B-W3-ParoQuant-WO
8B • Updated • 30 -
sy128/CQ3-Qwen3-8B-W2-ParoQuant-WO
8B • Updated • 14 -
sy128/CQ3-Qwen3-14B-W4-ParoQuant-WO
15B • Updated • 19 -
sy128/CQ3-Qwen3-14B-W3-ParoQuant-WO
15B • Updated • 19 -
sy128/CQ3-Qwen3-14B-W2-ParoQuant-WO
15B • Updated • 20 -
sy128/CQ3-Qwen3-32B-W4-ParoQuant-WO
33B • Updated • 17 -
sy128/CQ3-Qwen3-32B-W3-ParoQuant-WO
33B • Updated • 16 -
sy128/CQ3-Qwen3-4B-Thinking-2507-K8-SqueezeLLM
4B • Updated • 12 -
sy128/CQ3-Qwen3-32B-W2-ParoQuant-WO
33B • Updated • 20 -
sy128/CQ3-Qwen3-4B-Thinking-2507-K4-SqueezeLLM
4B • Updated • 17 -
sy128/CQ3-Qwen3-4B-Thinking-2507-K16-CodeQuant
4B • Updated • 15 • 1 -
sy128/CQ3-Llama-3.1-Nemotron-Nano-4B-v1.1-K8-SqueezeLLM
5B • Updated • 15 -
sy128/CQ3-Qwen3-4B-Thinking-2507-K8-CodeQuant
4B • Updated • 11 -
sy128/CQ3-Llama-3.1-Nemotron-Nano-4B-v1.1-K4-SqueezeLLM
5B • Updated • 13 -
sy128/CQ3-Qwen3-4B-Thinking-2507-K4-CodeQuant
4B • Updated • 15 • 2 -
sy128/CQ3-DeepSeek-R1-Distill-Llama-8B-K16-SqueezeLLM
8B • Updated • 15 -
sy128/CQ3-Llama-3.1-Nemotron-Nano-4B-v1.1-K16-CodeQuant
5B • Updated • 13 -
sy128/CQ3-Llama-3.1-Nemotron-Nano-4B-v1.1-K8-CodeQuant
5B • Updated • 13 • 3 -
sy128/CQ3-Llama-3.1-Nemotron-Nano-4B-v1.1-K4-CodeQuant
5B • Updated • 13 • 2 -
sy128/CQ3-DeepSeek-R1-Distill-Llama-8B-K16-CodeQuant
8B • Updated • 15 -
sy128/CQ3-DeepSeek-R1-Distill-Llama-8B-K8-CodeQuant
8B • Updated • 17 • 1 -
sy128/CQ3-DeepSeek-R1-Distill-Llama-8B-K4-CodeQuant
8B • Updated • 15 -
sy128/CQ3-Qwen3-4B-Thinking-2507-K16-SqueezeLLM
4B • Updated • 12 -
sy128/CQ3-DeepSeek-R1-Distill-Llama-8B-K8-SqueezeLLM
8B • Updated • 16 -
sy128/CQ3-DeepSeek-R1-Distill-Llama-8B-K4-SqueezeLLM
8B • Updated • 19