| ▲ | aliljet 3 hours ago | |
Where can a user reasonably host this in an affordable way to access the local LLM revolution? | ||
| ▲ | satvikpendem a minute ago | parent | next [-] | |
Unsloth Studio with its MTP support: https://unsloth.ai/docs/models/qwen3.6#mtp-guide | ||
| ▲ | julianlam an hour ago | parent | prev | next [-] | |
Try llama.cpp and Qwen3.6-35B-A3B Good balance of intelligence and speed. | ||
| ▲ | plagiarist 2 hours ago | parent | prev [-] | |
I think their Max models are far bigger than fits on consumer hardware. People are typically using Apple, AMD Halo, or dGPUs if/when they do smaller versions. Those are all varying degrees of "affordable." | ||