Comment on DeepSeek's distilled new R1 AI model can run on a single GPU | TechCrunch
avidamoeba@lemmy.ca 1 week agoIt proved sqrt(2) irrational with 40tps on a 3090 here. The 32b R1 did it with 32tps but it thought a lot longer.
Comment on DeepSeek's distilled new R1 AI model can run on a single GPU | TechCrunch
avidamoeba@lemmy.ca 1 week agoIt proved sqrt(2) irrational with 40tps on a 3090 here. The 32b R1 did it with 32tps but it thought a lot longer.
vhstape@lemmy.sdf.org 1 week ago
On my Mac mini running LM Studio, it managed 1702 tokens at 17.19 tok/sec and thought for 1 minute