On: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

[mitchell_h]

Tried. The context windows just weren't big enough.

[coder543 → mitchell_h]

Qwen3.6-27B supports a 1 million token context window.

Of course, you have to have the right hardware to be able to run with a context window like that, as it takes about 100GB of memory on my DGX Spark to do that with full f16 KV cache on the q4_k_xl model.

[lysace → mitchell_h]

Got a similar result (my RTX 4070 only has 12 GB). I'm curious about whether 24/32 GB meaningfully improves this enough to make it useful.

[tobyhinloopen → lysace]

Try it on RAM and CPU.

It’s slower but you can run them.

[lysace → tobyhinloopen]

Good idea for evaluating the models, thanks.

[deadbabe → mitchell_h]

Prompt more directly instead of open ended.