Avg. Total Time
17.25s
Avg. TTFT
2.16s
Avg. Prefill TPS
327.69
Avg. Gen TPS
8.42
Context Size
262144
Quantization
r32
Engine
vllm
Creation Method
LoRA Finetune
Model Type
Mistraltest
Chat Template
Mistral
Reasoning
Yes
Vision
No
Parameters
128B
Added At
5/5/2026
No Model Read Me file available.