I use Kimi K2.6 and Minimax 3. Both are mainly due to pricing.
I got 6 months of Google Pro from buying my new phone, so I use Gemini Pro 3.1 and Gemini 3 Flash quite a bit, but don’t think it does too well compared to Kimi and Minimax.
I use Opus 4.6 as I get some usage from Google Pro, but it’s just like 1 task or something.
It is obviously the best, but considering the usage is extremely expensive, and I can use Kimi and Minimax almost 100x as much with a subscription. It kinda becomes a worse model. I’d rather Kimi working really long on a problem, than a slightly more powerful model with almost no usage. I can get a lot more done with high quality results from Kimi due to this.
What models are you using, and why?
(Sorry of discussions are not allowed in this community)
Qwen3.6 27B works well enough with a decent harness
Interesting, can it do larger tasks? Or do you use it for Openclaw/Hermes?
use it inside claude. does decent. I generally dont assign AI models large free form tasks. they all suck at them from my experience.
I usually stick to planing + execution modes for straight forward task.
I did not know you could use 3rd party models in Claude, is it better than OpenCode? Or is it its own Hermes/Openclaw thing?
i havent compared it to other model runners. havent really felt the need. my concern was always local host first. =)
and yeah claude has environment variables you can just point at different endpoints.
I just uncomment the exports at the end when i want to enable my local model.
cat ~/.bashrc.d/claude.sh unset ANTHROPIC_AUTH_TOKEN unset ANTHROPIC_BASE_URL unset ANTHROPIC_API_KEY unset ANTHROPIC_MODEL # https://github.com/ggml-org/llama.cpp/issues/20003 # https://github.com/ggml-org/llama.cpp/pull/20087 #export CLAUDE_CODE_ATTRIBUTION_HEADER=0 #export ANTHROPIC_AUTH_TOKEN=ollama #export ANTHROPIC_API_KEY="" #export ANTHROPIC_BASE_URL=http://localhost:11434/Interesting, I should probably check it out. I use OpenCode currently, but it is always interesting to try other tools