Comment by syntaxing
7 days ago
I don’t know if the llama cpp implementation is wonky (and only supports the binary version) but it’s a lot slower than 35B-A3B @ Q4_KM + MTP with CPU offloading.
7 days ago
I don’t know if the llama cpp implementation is wonky (and only supports the binary version) but it’s a lot slower than 35B-A3B @ Q4_KM + MTP with CPU offloading.
It’s still a dense model so all 27B parameters are active. 35B-A3B activates only 3B at any time.
Most probably not optimized yet for this model...