Hourly Usage
Performance Metrics
Median Total Time
7.36s
Median TTFT
2.50s
Median Prefill TPS
2986.77
Median Gen TPS
40.66
Model Information
Context Size
262144
Quantization
r64 on FP8
Engine
vllm
Creation Method
Finetune
Model Type
Qwen35
Chat Template
Qwen3.5
Reasoning
Yes
Vision
Yes
Parameters
27B
Added At
4/21/2026
No Model Read Me file available.