mini-coder: small models for agentic SWE research

Ricardo Olmedo

Max Planck Institute for Intelligent Systems, Tübingen

September 30, 2025

SWE-bench Verified (Bash only)

	pass@1	pass@100
Qwen 3 Coder 30B-A3B	33.2	67.4
mini-coder-4b	26.8	60.2
gpt-oss-120b	26.0	-
mini-coder-1.7b	18.6	50.4
SWE-agent-LM 7B	15.2	-
Qwen 3 4B Instruct 2507	4.0	25.1

Small models play a crucial role in today's research ecosystem. They enable a larger pool of researchers to contribute to the field, thereby accelerating scientific progress. Unfortunately, the entry barrier for agentic SWE research remains high: performant open-weight models are in the 30B-parameter range. To make matters worse, SWE agentic tasks require long, multi-turn interactions, further increasing GPU memory demands. As a result, research on post-training SWE agents generally requires multi-GPU—and often multi-node—setups.

To lower this entry barrier, we trained mini-coder: two small but performant agentic SWE models. We follow a straightforward training recipe: distillation from a larger, more capable model. We distill from Qwen 3 Coder 30B, which strikes a good balance between performance and inference cost. Using the SWE-smith dataset of GitHub issues, together with the lightweight mini-swe-agent scaffolding, we generated 400k training trajectories (~5.5B tokens). We then fine-tuned Qwen 3 1.7B and Qwen 3 4B Instruct on these trajectories.

The mini-coder models deliver SOTA performance on SWE-Bench Verified Bash-only at their size. Remarkably, mini-coder-4b matches the performance of the much larger gpt-oss-120b, while mini-coder-4b outperforms SWE-Agent-LM 7B. The two models also achieve much higher pass@k than their corresponding base models. This indicates that the mini-coder models are strong candidates for RL fine-tuning, since pass@k reflects the fraction of problems from which effective supervision can be derived.

Unlike existing agentic SWE models, the mini-coder models can be post-trained on a single 80GB GPU—or smaller. They work seamlessly with mini-swe-agent, a lightweight, scalable, and developer-friendly agentic framework well-suited for RL fine-tuning. And because they are dense rather than MoE models, they benefit from a more mature fine-tuning ecosystem. Additionally, researchers can incorportate our dataset of 400k training trajectories in their post-training recipes. All in all, we hope that the mini-coder models will accelerate progress in agentic SWE research.