I'm currently running experimental version of llama.cpp in order to get the new Qwen3.8-Flash-Next to run. It's running incredibly well. We'll see what it produces.
3.06M sat
I'm currently running experimental version of llama.cpp in order to get the new Qwen3.8-Flash-Next to run. It's running incredibly well. We'll see what it produces.
Base M4 Mac mini would be pretty useless for this right?
Fields the transaction did not carry are omitted. Open the payload to see the bytes as stored.
1Dv2xCbVs53RN66Jhwi2HBQbenTLKZojVb Unverified