GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
AI4SGI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AI4SGI
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
Browse the complete release in the ExoMind Model Family.
| Model | Format | Hugging Face | ModelScope |
|---|---|---|---|
| ExoMind | 35B-A3B Transformers | Model | Model |
| ExoMind-Q4_K_M-GGUF | 35B-A3B Q4_K_M GGUF | Model | Model |
| ExoMind-Q8_0-GGUF | 35B-A3B Q8_0 GGUF | Model | Model |
| ExoMind-F16-GGUF | 35B-A3B F16 GGUF | Model | Model |
| ExoMind-9B | 9B Transformers | Model | Model |
| ExoMind-9B-Q4_K_M-GGUF | 9B Q4_K_M GGUF | Model | Model |
| ExoMind-9B-Q8_0-GGUF | 9B Q8_0 GGUF | Model | Model |
| ExoMind-9B-F16-GGUF | 9B F16 GGUF | Model | Model |
ExoMind-9B is the compact ExoMind checkpoint, fine-tuned from Qwen3.5-9B for lower-resource experimentation in scientific reasoning and agentic research. It follows the same extended-mind-inspired approach, organizing the model, specialized interaction objects, and autonomous interaction processes as one system.
Use a recent vLLM or SGLang release with Qwen3.5 support. The examples below use the checkpoint's configured maximum context length of 262,144 tokens.
bash
vllm serve AI4SGI/ExoMind-9B \--port 8000 \--tensor-parallel-size 1 \--max-model-len 262144 \--reasoning-parser qwen3 \--enable-auto-tool-choice \--tool-call-parser qwen3_coder
bash
python -m sglang.launch_server \--model-path AI4SGI/ExoMind-9B \--host 0.0.0.0 \--port 8000 \--tp-size 1 \--context-length 262144 \--reasoning-parser qwen3 \--tool-call-parser qwen3_coder
python
from openai import OpenAIclient = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")response = client.chat.completions.create(model="AI4SGI/ExoMind-9B",messages=[{"role": "user","content": "Develop a testable hypothesis and a rigorous verification plan for: ...",}],temperature=1.0,top_p=0.95,extra_body={"top_k": 20},)print(response.choices[0].message.content)
The table below reports the main ExoMind 35B-A3B system. ExoMind-9B is provided as a compact checkpoint and has not been assigned these scores.
Complete settings and comparisons are available in the evaluation explorer.
ExoMind-9B is intended for scientific question answering, mathematical and computational reasoning, tool-use experiments, code-assisted verification, and resource-conscious agentic prototypes.
The distributed checkpoint and upstream Qwen3.5 materials are provided under the Apache License 2.0 included in this repository. The technical report, scientific figures and results, and ExoMind brand assets are subject to the ExoMind Research Content and Brand Terms. See NOTICE.md for third-party notices.
bibtex
@misc{exomind2026,title = {ExoMind: Democratizing Scientific Intelligence via Extended-Mind-Inspired Agentic System},author = {Peng Ye and Zhuo Liu and Jingqi Ye and Fangchen Yu and Shengji Tang and Yichen Jiang and Haonan He and Zongsheng Cao and Tao Chen and Bo Zhang and Wanli Ouyang and Bowen Zhou and Lei Bai},year = {2026},note = {Technical report},url = {https://github.com/AI4SGI/ExoMind/blob/main/Paper.pdf}}