News for hackers. Stuff that matters.

A comment on Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per Second. Parent comment

Re:Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per ... by throwaw12 on Wednesday July 23, 2025 @08:32AM (#44658484)
Have you used Claude Code and how do you compare the quality to Claude models? I am heavily invested in tools around Claude, still struggling to make a switch and start experimenting with other models
[ Parent | on HN ]
Re:Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per ... by meowface on Wednesday July 23, 2025 @11:33AM (#44660371)
I still exclusively use Claude Code. I have not yet experimented with these other models for practical software development work.

A workflow I've been hearing about is: use Claude Code until quota exhaustion, use Gemini CLI with Gemini 2.5 Pro free credits until quota exhaustion, then use something like a cheap-ish K2 or Qwen 3 provider, with OpenCode or the new Qwen Code, until your Claude Code credits reset and you begin the cycle anew.

[ Parent | on HN ]
Re:Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per ... by bredren on Wednesday July 23, 2025 @08:40AM (#44658543)
Are you using Claude code or the web interface? I would like to try this with CC myself, apparently with some proxy use an OpenAI compatible LLM can be swapped in.
[ Parent | on HN ]
Re:Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per ... by throwaw12 on Wednesday July 23, 2025 @08:42AM (#44658579)
I am using Claude code, my experience with it so far is great. I use it primarily from terminal, this way I stay focused while reading code and CC doing its job in the background.
[ Parent | on HN ]
Re:Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per ... by bredren on Wednesday July 23, 2025 @08:55AM (#44658688)
I’ve heard this repeated that using the env vars you can use gpt models, for example.

But then also that running a proxy tool locally is needed.

I haven’t tried this setup, and can’t say offhand if Cerebras’ hosted qwen described here is “OpenAI” compatible.

I also don’t know if all of the tools CC uses out of the box are supported in the most compatible non-Anthropic models.

Can anyone provide clarity / additional testimony on swapping out the engine on Claude Code?

[ Parent | on HN ]
Re:Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per ... by derac on Wednesday July 23, 2025 @09:46AM (#44659201)
I've used Kimi K2, it works well. Personally I'm using Claude Code Router.

https://github.com/musistudio/claude-code-router

[ Parent | on HN ]