I agree. I much prefer OpenCode (with the web UI). My idea combo would be Claude models with opencode but of course that is far more expensive because Anthropic wants to lock you in.
The inertia of switching. At least for me, being able to maintain the same UX and configuration for agentic coding is a benefit. I have access to internal models at work where I use a LiteLLM proxy with Claude Code, so no Anthropic models, but I can maintain the same .claude between personal and work machines. Though I'm definitely open to a non-Anthropic harness if it's a clear win.
Doing anything special to handle the syncing of .claude? Kind of a pain point for me jumping between Windows/Linux and having to deal with path differences.
Fair question. I haven’t benchmarked it against other harnesses, so I can’t say it’s better.
My reason for using claude code is continuity - I use it for dev (it’s also the tool of choice for most people I work with), and it already has the context. And it supports both frontier and OSS models.
i don't understand why people would ever want to read this kind of article. The information is ok, but it's a regurgitation of many sources, some of it incorrect, covered in ai slop prose.
Please share the cool thing you're doing in a blog post, but don't have AI write it for you; it's hard to read and doesn't respect the reader
I understand why local, I don't understand why Claude Code. Is it better than the other harnesses?
I thought the main reason for using Claude Code was that it was the only harness one was allowed to use with the Claude subscription plan...
I agree. I much prefer OpenCode (with the web UI). My idea combo would be Claude models with opencode but of course that is far more expensive because Anthropic wants to lock you in.
Its an experiment worth trying - swap out Claude Code for OpenCode and run the benchmark. I'll try it out.
The inertia of switching. At least for me, being able to maintain the same UX and configuration for agentic coding is a benefit. I have access to internal models at work where I use a LiteLLM proxy with Claude Code, so no Anthropic models, but I can maintain the same .claude between personal and work machines. Though I'm definitely open to a non-Anthropic harness if it's a clear win.
Doing anything special to handle the syncing of .claude? Kind of a pain point for me jumping between Windows/Linux and having to deal with path differences.
Yes!! And your LiteLLM-proxy-to-internal-models setup is a cleaner setup than mine.
Fair question. I haven’t benchmarked it against other harnesses, so I can’t say it’s better.
My reason for using claude code is continuity - I use it for dev (it’s also the tool of choice for most people I work with), and it already has the context. And it supports both frontier and OSS models.
Most reports I ahve seen have 27b (which is dense) being much more performant then 35b (MoE). Is there a reason for 35b?
I am using qwen3.6:35b-a3b-coding-nvfp4, active 3b. Easier on my hardware - Mac M3 Pro.
i don't understand why people would ever want to read this kind of article. The information is ok, but it's a regurgitation of many sources, some of it incorrect, covered in ai slop prose.
Please share the cool thing you're doing in a blog post, but don't have AI write it for you; it's hard to read and doesn't respect the reader
[dead]
[flagged]