Arao AI
Back to search results

elephant-1 · IQ3_XS

Start a discussion
NVIDIA RTX 508016GBllama.cpp v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of elephant-1 (IQ3_XS) on NVIDIA RTX 5080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

196.47 tok/s

Decode

Decode speed

707.56 tok/s

Prefill

Prefill speed

2.07 s

TTFT

Time to first token

13.82 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

14 days ago

Last verified

Performance

  1. llama.cpp · IQ3_XS (current)Decode 196.47 · Prefill 707.56 ·

Core figures

Decode (avg)
196.47 tok/s
Prefill (avg)
707.56 tok/s
TTFT (avg)
2.07 s
VRAM (avg)
13.82 GB
MTP acceptance rate
—
TTFB
1.57 GB
Power draw
275.1 W

Configuration

Member-level fields are taken from the most recent run

Model
elephant-1
Quantization
IQ3_XS
Framework
llama.cpp
Version
v0.31
Context length
2048 tokens
Batch size
256
GPU layers
99
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
13.82 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
275.1 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-22

    v0.31 · Ubuntu 22.04 · CUDA 12.6 · 2048 ctx

    196.47 tok/s

    Decode

    707.56 tok/s

    Prefill

    2.07 s

    TTFT

    13.82 GB

    VRAM

    —

    MTP

    275.1 W

    Power draw

    L2 batch seed 2026-10-22: llama.cpp on hw_id=14 running model_id=95 at IQ3_XS