Hourly Usage
Performance Metrics
Typical Total Time
2.34s
Typical TTFT
0.74s
Typical Input TPS
1135.72
Typical Output TPS
26.74
Model Information
Context Size
262144
Quantization
r64 on INT8
Engine
vllm
Creation Method
Finetune
Model Type
Qwen35
Chat Template
Qwen3.5
Reasoning
Yes
Vision
Yes
Parameters
27B
Added At
4/27/2026
No Model Read Me file available.