@[email protected] to [email protected] • 1 month agoDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square25fedilinkarrow-up1141cross-posted to: [email protected]
arrow-up1141external-linkDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.com@[email protected] to [email protected] • 1 month agomessage-square25fedilinkcross-posted to: [email protected]
minus-square@[email protected]linkfedilink5•edit-21 month agoThe hell is v3 32b. Are you talking about a distill
minus-square@[email protected]linkfedilinkDeutsch1•1 month agoThey probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.
The hell is v3 32b. Are you talking about a distill
They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.