Accurate FP8 quantized deepseek R1 distilled models, ready for use with SGLang and vLLM!
-
JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-1.5B-FP8-Dynamic
Text Generation • Updated -
JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-7B-FP8-Dynamic
Text Generation • Updated • 247 • 1 -
JamAndTeaStudios/DeepSeek-R1-Distill-Llama-8B-FP8-Dynamic
Text Generation • Updated • 44 • 1 -
JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-14B-FP8-Dynamic
Text Generation • Updated • 1.28k • 1