Instructions to use Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B") model = AutoModelForMultimodalLM.from_pretrained("Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B
- SGLang
How to use Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B with Docker Model Runner:
docker model run hf.co/Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B
Logics-SWE-Qwen3.6-35B-A3B
Logics-SWE-Qwen3.6-35B-A3B is a software engineering model developed from Qwen3.6-35B-A3B using category-aware multi-teacher on-policy distillation (MOPD). It brings together the capabilities of three software engineering experts in a single model for repository-level coding agents.
Paper · GitHub: AgenticBigBang · Logics-SWE-Qwen3.6-27B · Dataset: Logics-SWE-Env-2.5K
📰 News
- [2026.10.30] Introduced Logics-SWE-Qwen3.6-35B-A3B, trained with MOPD using the same three 27B category experts as Logics-SWE-Qwen3.6-27B.
Highlights
- One policy, three experts. The model integrates three category experts into one student that can work across repository domains without selecting an expert at inference time.
- Reuse of 27B teachers. The same three final Qwen3.6-27B-based experts used for Logics-SWE-Qwen3.6-27B are reused to train the 35B-A3B student.
- Improved SWE and coding results. Compared with Qwen3.6-35B-A3B, the model improves by 3.69 points on SWE-bench Pro V2, 3.00 points on SWE-bench Multilingual, and 2.37 points on SWE-bench Pro.
How It Works
Repository-level software engineering tasks span different domains, from services and data systems to user-facing applications and developer tools. The RRE–MOPD approach develops complementary specialists and combines their knowledge into a single agent model:
- Organize tasks. SWE Labeler assigns tasks to repository-domain categories: service, data and security; user-facing applications; and systems, tooling and runtimes.
- Develop experts. Three Qwen3.6-27B-based experts are trained with Refresh–Repair–Expand (RRE), alternating agentic reinforcement learning, mastery refreshes, and supervised repair on verified successful trajectories.
- Integrate with MOPD. A student initialized from Qwen3.6-35B-A3B generates its own trajectories and receives token-level guidance from the expert corresponding to each training task. The student's initial policy serves as the frozen reference for extrapolation.
The final model runs as a single policy. It does not require the three experts or category routing when deployed.
Experimental Results
The table shows three-round mean scores (%) for the full model-and-agent evaluation setups. Improvements are percentage points over Qwen3.6-35B-A3B.
| Evaluation | Tasks per round | Qwen3.6-35B-A3B | Logics-SWE-Qwen3.6-35B-A3B | Improvement |
|---|---|---|---|---|
| SWE-bench Pro V2 | 642 | 73.31 | 77.00 | +3.69 |
| SWE-bench Pro V2 Hard-51 | 51 | 28.10 | 33.99 | +5.88 |
| SWE-bench Multilingual | 300 | 63.44 | 66.44 | +3.00 |
| SWE-bench Pro | 731 | 48.75 | 51.12 | +2.37 |
| LiveCodeBench v6 | 175 | 76.95 | 78.10 | +1.14 |
Hard-51 is a subset of SWE-bench Pro V2. Differences are calculated before rounding the displayed scores.
Intended Use
The model is intended for research and development on repository-level software engineering agents, including codebase exploration, issue diagnosis, code editing, test execution, and iterative debugging. A coding-agent harness can provide the model with repository access, tools, execution feedback, and a workspace in which to build and validate a patch.
Serving
For a local copy of the model, a vLLM server can be started with:
vllm serve /path/to/Logics-SWE-Qwen3.6-35B-A3B
The server exposes an OpenAI-compatible API for integration with a coding-agent harness. Use the model's tokenizer and chat template when constructing requests. See the Qwen model card and vLLM documentation for serving setup.
Data and Resources
The public Logics-SWE-Env-2.5K release provides 2,553 software engineering task instances and matching environment-image references. The AgenticBigBang repository contains SWE Labeler, research artifacts, and evaluation materials.
Citation
If you use this work, please cite:
@misc{zhao2026onetomoremoretoone,
title = {One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents},
author = {Jie Zhao and Ziyu Jiang and Suhang Zheng and Minghui Shan and Xiaoxiao Xu and Lin Qu},
year = {2026},
eprint = {2609.23377},
archivePrefix = {arXiv},
primaryClass = {cs.SE},
url = {https://arxiv.org/abs/2609.23377}
}
Acknowledgements
We thank the Qwen, ROLL, R2E-Gym, SWE-agent, SWE-bench, SWE-bench Pro, and SWE-bench Multilingual contributors, and the research communities behind MiniRL, MOPD, and ExOPD.
License
Model license: Apache License 2.0.
- Downloads last month
- 1,099
Model tree for Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B
Dataset used to train Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B
Spaces using Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B 2
Paper for Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B
Evaluation results
- ScaleAI/SWE-bench_Pro leaderboard
- SWE Bench Pro View evaluation resultsSWE-bench Pro V2, 642 tasks; mean of three rounds; mini-SWE-agent 2.4.6 with patch replay.77 *
- SWE Bench Pro Hard View evaluation resultsThree-round mean; 51-task Pro V2 subset; mini-SWE-agent 2.4.6 with patch replay.33.99 *
- SWE-bench/SWE-bench_Multilingual · Swe Bench Multilingual Resolved View evaluation results leaderboard 66.44 *

docker model run hf.co/Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B