MIT-licensed agentic models (9B–397B) trained with RL to optimize both solution rollouts and search scaffolds, available in dense and MoE variants with 256K context and OpenAI-compatible serving.
Summary
Replaces closed-model dependency for agentic coding workflows; dense 9B runs on single 80GB GPU, MoE variants shard across multi-GPU nodes. Benchmark numbers show competitive or better performance than comparable open baselines on SWE-bench, Terminal-Bench, and NL2Repo.
Why it matters
Replaces closed-model dependency for agentic coding workflows; dense 9B runs on single 80GB GPU, MoE variants shard across multi-GPU nodes. Benchmark numbers show competitive or better performance than comparable open baselines on SWE-bench, Terminal-Bench, and NL2Repo.
Implementation verdict
Production-ready for self-hosted deployment. Requires transformers ≥5.8.1, vLLM ≥0.19.1, or SGLang ≥0.5.9. Model outputs reasoning traces in <think> blocks; parsers surface tool_calls and reasoning_content separately. Dense 9B is lowest-friction entry point; MoE 35B/397B demand multi-GPU infrastructure. Worth trying now if you control serving infra.
Sources
Dev Signal
Get briefs like this in your inbox — free, every weekday.
100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.