Re-introduces a small curated list of models that ship preconfigured
in Atomic Chat, so opencode users get a working `models.dev` entry
out of the box instead of an empty `models: {}`.
Models (ids match the normalized form returned by Atomic Chat's
/v1/models endpoint, i.e. dots replaced with underscores):
- gemma-4-E4B-it-IQ4_XS
- gemma-4-E4B-it-MLX-4bit
- Qwen3_5-9B-Q4_K_M
- Qwen3_5-9B-MLX-4bit
- Meta-Llama-3_1-8B-Instruct-GGUF
Qwen 3.5 9B dates are taken from the verified providers/venice entry
for the same base model; quantization does not change release dates.
Made-with: Cursor
Adds Atomic Chat as a local OpenAI-compatible provider at
http://127.0.0.1:1337/v1. Includes logo and three curated models:
- unsloth/Qwen3.5-9B-IQ4_XS (id: Qwen3_5-9B-IQ4_XS)
- unsloth/gemma-4-E4B-it-IQ4_XS (id: gemma-4-E4B-it-IQ4_XS)
- unsloth/MiniMax-M2.5-UD-TQ1_0 (id: MiniMax-M2_5-UD-TQ1_0)
Model ids match the normalized form returned by Atomic Chat's
/v1/models endpoint (dots replaced with underscores).
Made-with: Cursor
Adam