GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
contextboxai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
contextboxai
Model Tree
google/gemma-4-31B-it
Input Modalities
Output Modalities
Supported Functionality
Tested configuration: 1x H100 80GB, vLLM 0.28.0.
bash
pip install vllm==0.28.0 transformersvllm serve contextboxai/Can-1.0-31B --served-model-name jevbeat --port 8890 \ --max-model-len 12288 --gpu-memory-utilization 0.95 --max-logprobs 20# decision server (POST :8011/v1/systemone); states over JB_MAX_STATE tokens are truncated head 60% / tail 40%, never refusedJB_TOKENIZER=contextboxai/Can-1.0-31B JB_CALIB=calib.json JB_MAX_STATE=10000 python serve/server.pyOptional (not tested by us): with more GPU memory (e.g. --tensor-parallel-size 2 --max-model-len 98304), raise
JB_MAX_STATE to ~90000 to read the longest states in full.
Request: {"state": ..., "questions": {"decision": {"type": ..., "instructions": ..., "criteria": ...}}}.
Response: {"model", "answers": {"decision": {...}}, "usage": {"prompt_tokens", "completion_tokens", "total_tokens"}}.
More than 10 options -> HTTP 422.
Proxy slices (ours; not the official benchmark). Capability = (I + C) / 2 after calibration; paired doc-bootstrap where noted.
| slice | items | I | C | Capability | Quyet-1.0-Large (same harness, its own runtime) |
|---|---|---|---|---|---|
| TypeSafe evalsafe documents | 3030 | 57.3 | 90.9 | 74.1 | 68.8 |
| law / rules / math (LegalBench, MMLU-Pro, GSM8K) | 2295 | 74.4 | 90.1 | 82.2 | 84.7 |
| code (CRUXEval, HumanEval, MBPP; execution-verified) | 410 | 83.6 | 93.3 | 88.5 | 88.8 |
| multilingual (Global-MMLU, Belebele; 10 languages) | 500 | 68.5 | 89.2 |
Single forward pass, raw p50 latency 0.03 s on one H100 (vLLM).
Never trained on JevBench items or anything taken from the benchmark. Evaluation-only sources (LegalBench, MMLU-Pro, GSM8K, CRUXEval, HumanEval, MBPP, Global-MMLU, Belebele, TypeSafe evalsafe) were excluded from training and checked by 13-gram overlap.
Apache-2.0. See NOTICE: Gemma 4 by Google (Apache-2.0); pplx-decider-v1.1-27b by Perplexity (Apache-2.0, used as a
teacher); tasksource by Damien Sileo (per-dataset licences; non-commercial rows excluded).
Built by ContextBox AI.
| 78.9 |
| 81.6 |
| hand-written hard rules (fictional statutes; held out) | 100 | 68.4 | 69.6 | 69.0 | 70.1 |