unsloth desktop provider support

[texastoland]

currently works as /login llama.cpp w/ env:

export LLAMA_CPP_BASE_URL=http://127.0.0.1:8888/v1

[rafde]

can't you update your model.yml file?

providers:
  rtx3090Unsloth:
    baseUrl: http://127.0.0.1:8889/v1
    apiKey: sk-unsloth-key
    api: openai-completions
    models:
      - id: unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
        name: Qwen3-Coder-30B-A3B-Instruct (3090)
        contextWindow: 262144
        maxTokens: 65536

[texastoland]

compared to a single click or single env? if manually updating model configs is your jam then rock on 🤘🏼 switched back to lm studio for now anyway