JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-1.5B-FP8-Dynamic
Text Generation • 2B • Updated •
1
updated
Accurate FP8 quantized deepseek R1 distilled models, ready for use with SGLang and vLLM!
Text Generation • 2B • Updated •
1
Text Generation • 8B • Updated •
1 •
1
Text Generation • 8B • Updated •
2 •
1
Text Generation • 15B • Updated •
2 •
1
Text Generation • 33B • Updated •
585 •
2
Text Generation • 71B • Updated •
2