GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
SurdAI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
SurdAI
Model Tree
Qwen/Qwen3.6-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
bash
pip install huggingface_hubhf download SurdAI/SPX-CD-Flash --local-dir SPX-CD-Flashcd SPX-CD-FlashUse separate environments for the two backends. Install CUDA-enabled PyTorch for Transformers; install the vLLM requirements in a clean environment.
Transformers, BF16 base:
bash
pip install -r requirements-transformers.txtpython infer.py --backend transformers --adapter . \ --input examples/text.json --output predictions.jsonlvLLM, compatible 4-bit base:
bash
pip install -r requirements-vllm.txtpython infer.py --backend vllm --base /path/to/compatible-4bit-base \ --adapter . --effort 2 --input examples/text.json --output predictions.jsonlUse a compatible 4-bit quantization of Qwen/Qwen3.6-35B-A3B with its matching processor. The inference backend must support both that quantization format and this LoRA adapter; 4-bit formats are not interchangeable. The exact evaluated configuration is recorded in EVALUATION.md.
For images or multi-select, use examples/image.json or examples/multi_select.json. See these files for the input format and python infer.py --help for options. Image paths are relative to the input file, or to --image-root when specified.
Completed CMDB-1500 evaluation, effort 2, 4-bit base, vLLM:
| Scope | Questions | Accuracy |
|---|---|---|
| Text | 1,200 | 77.58% |
| Images | 300 | 87.33% |
| All | 1,500 | 79.53% |
All 1,500 questions produced valid predictions. Evaluation settings are in EVALUATION.md; machine-readable results are in evaluation_results.json.
The SurdAI release page reports the following results:
| Effort | JevBench Public (231) | JevBench Hard (111) | Decision Index 0.2.1 ↑ |
|---|---|---|---|
| 1 | 88.31% (204/231) | 77.48% (86/111) | 54.65 |
| 2 | 89.18% (206/231) | 77.48% (86/111) | — |
Hard 111 is a subset of Public 231. Decision Index uses its own score scale. These results use the serving configurations described on the linked release page.
--max-context: default 65,536 total tokens. Each scoring pass reserves one output token, leaving at most 65,535 prompt tokens, including image tokens, candidates, and selected-label prefixes. Reduce this setting if needed for available memory.--effort 1–5: average distinct candidate orderings, capped at two for binary questions. Default 1; the CMDB results use 2.--temperature: candidate-softmax temperature, default 1.0.--prompt-format: cmdb for text and image decisions; open-format for text single-choice tasks.Apache 2.0 for this adapter and included code. The base model is distributed separately under its own model card. Verify release files with checksums.json. Release identity and original weight SHA-256 are recorded in release.json.
pip install huggingface_hubhf download SurdAI/SPX-CD-Flash --local-dir SPX-CD-Flashcd SPX-CD-Flashpip install -r requirements-transformers.txtpython infer.py --backend transformers --adapter . \ --input examples/text.json --output predictions.jsonlpip install -r requirements-vllm.txtpython infer.py --backend vllm --base /path/to/compatible-4bit-base \ --adapter . --effort 2 --input examples/text.json --output predictions.jsonl