Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
by amelius on Saturday November 14, 2026 @09:53AM
(#50497497)
What harnesses are people creating to make the local models act more like Claude?
[ Parent
| on HN ]
Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
by SamInTheShell on Saturday November 14, 2026 @10:29AM
(#50497795)
If you look through the ollama codebase, it has a bunch of helpers for just pointing claude code, codex, etc at the ollama api. You can just use ollama and it's helpers or just write your own wrapper to make it work however you want.
Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
by amelius on Saturday November 14, 2026 @11:35AM
(#50498355)
Well, I want Claude Code, Opus 5.5 specifically, but locally. I assume that if you give e.g. Qwen a certain set of instructions (skills, etc.) or complete harness, you can make it behave more like Claude. And I assume there are people who are trying to do this. So that's what I'm asking.
Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
by exe34 on Saturday November 14, 2026 @01:25PM
(#50499427)
I'm just trying out Claude Code against this model (q4). It's dog slow right now. It hasn't finished yet, and I'll get Opus to grade it.
Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
by WhyNotHugo on Saturday November 14, 2026 @04:49PM
(#50501275)