Supra2-Medium-Base is a 25M parameter LLM trained from scratch

Built on the Qwen3 architecture, it benchmarks competitively with the developer's previous 50M-parameter Supra-50M-Base. Training ran on an RTX 5060 Ti 16GB and RTX 5060 8GB rig.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- LangSmith adds Preview Builds to test agent changes before production
- Exa plugin gives ChatGPT Work and Codex access to 100B+ websites
- Ramp launches its own AI model router, called Router
- Apple’s AirPods Should Avoid Meta’s Mistakes
- Docker's Tushar Jain on AI-native runtime for agent autonomy