Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by coder543 on Thursday April 16, 2026 @11:17AM (#47794460)

Not true. With a MoE, you can offload quite a bit of the model to CPU without losing a ton of performance. 16GB should be fine to run the 4-bit (or larger) model at speeds that are decent. The --n-cpu-moe parameter is the key one on llama-server, if you're not just using -fit on.

[ Parent | on HN ]

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by boppo1 on Thursday April 16, 2026 @02:57PM (#47797871)

I've been way out of the local game for a while now, what's the best way to run models for a fairly technical user? I was using llama.cpp in the command line before and using bash files for prompts.

[ Parent | on HN ]

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by adrian_b on Thursday April 16, 2026 @06:17PM (#47800239)

Running llama-server (it belongs to llama.cpp) starts a HTTP server on a specified port.

You can connect to that port with any browser, for chat.

Or you can connect to that port with any application that supports the OpenAI API, e.g. a coding assistant harness.

[ Parent | on HN ]