Llama-3.3+(3.1v3.3)-70B-FLDx2 - Arli AI - Arli AI

Llama-3.3+(3.1v3.3)-70B-FLDx2

All-around Model

View on Hugging Face Back to Models

Hourly Usage

Performance Metrics

Avg. Total Time

6.79s

Avg. TTFT

6.35s

Avg. Prefill TPS

137.39

Avg. Gen TPS

20.45

Model Information

Context Size

32768

Quantization

r64

Engine

aphrodite

Creation Method

FFT

Model Type

Llama70B

Chat Template

Llama 3

Reasoning

No

Vision

No

Parameters

70B

Added At

1/13/2025

No Model Read Me file available.