21–30 of 223 posts
Earlier quoted context omitted.
End users -- people who use harnesses -- have subscriptions so that makes no sense. General API usage is for production.
"Production" what? The API is for using the model directly with your own tools. It can be in dev, or experiments, or anything. Subscriptions are for using the apps Claude + code. That's what it always said when you sign up.
Wildly understating this part.
Even the best local models (ones you run on beefy 128GB+ RAM machines) get nowhere close to the sheer intelligence of Claude/Gemini/Codex. At worst these models will move you backwards and just increase the amount of work Claude has to do when your limits reset.
Earlier quoted context omitted.
can you recommend a setup with ollama and a cli tool? Do you know if I need a licence for Claude if I only use my own local LLM?
What are your needs/constraints (hardware constraints definitely a big one)? The one I mentioned called continue.dev [1] is easy to try out and see if it meets your needs. Hitting local models with it should be very easy (it calls APIs at a specific port) [1] - https://github.com/continuedev/continue
For a full claude code replacement I'd go with opencode instead, but good models for that are something you run in your company's basement, not at home
Among these, I had lots of trouble getting GLM-4.7-Flash to work (failed tool calls etc), and even when it works, it's at very low tok/s. On the other hand Qwen3 variants perform very well, speed wise. For local sensitive document work, these are excellent; for serious coding not so much.
One caviat missed in most instructions is that you have to set CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC = 1 in your ~/.claude/settings.json, otherwise CC's telemetry pings cause total network failure because local ports are exhausted.
[1] claude-code-tools local LLM setup: https://github.com/pchalasani/claude-code-tools/blob/main/do...
My experience thus far is that the local models are a) pretty slow and b) prone to making broken tool calls. Because of (a) the iteration loop slows down enough to where I wander off to do other tasks, meaning that (b) is way more problematic because I don't see it for who knows how long. This is, however, a major improvement from ~6 months ago when even a single token `hi` from an agentic CLI could take >3 minutes t…
Closed models are specifically tuned with tools, that model provider wants them to work with (for example specific tools under claude code), and hence they perform better.
I think this will always be the case, unless someone tunes open models to work with the tools that their coding agent will use.
Will it work? Yes. Will it produce same quality as Sonnet or Opus? No.
> Reduce your expectations about speed and performance! Wildly understating this part. Even the best local models (ones you run on beefy 128GB+ RAM machines) get nowhere close to the sheer intelligence of Claude/Gemini/Codex. At worst these models will move you backwards and just increase the amount of work Claude has to do when your limits reset.
> Reduce your expectations about speed and performance! Wildly understating this part. Even the best local models (ones you run on beefy 128GB+ RAM machines) get nowhere close to the sheer intelligence of Claude/Gemini/Codex. At worst these models will move you backwards and just increase the amount of work Claude has to do when your limits reset.
The best open models such as Kimi 2.5 are about as smart today as the big proprietary models were one year ago. That's not "nothing" and is plenty good enough for everyday work.