Arao AI
Back to search results

elephant-1 · IQ2_XS

Start a discussion
NVIDIA RTX 409024GBvLLM v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of elephant-1 (IQ2_XS) on NVIDIA RTX 4090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

179.71 tok/s

Decode

Decode speed

772.31 tok/s

Prefill

Prefill speed

1.05 s

TTFT

Time to first token

11.17 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

13 days ago

Last verified

Performance

  1. llama.cpp · IQ1_S Decode 180.81 · Prefill 654.72 ·
  2. llama.cpp · IQ3_XS Decode 136.35 · Prefill 504.8 ·
  3. vLLM · IQ2_XS (current)Decode 179.71 · Prefill 772.31 ·

Core figures

Decode (avg)
179.71 tok/s
Prefill (avg)
772.31 tok/s
TTFT (avg)
1.05 s
VRAM (avg)
11.17 GB
MTP acceptance rate
—
TTFB
1.44 GB
Power draw
394.8 W

Configuration

Member-level fields are taken from the most recent run

Model
elephant-1
Quantization
IQ2_XS
Framework
vLLM
Version
v0.37
Context length
32768 tokens
Batch size
8
GPU layers
999
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
11.17 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.4
Power draw
394.8 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

    v0.37 · Ubuntu 24.04 · CUDA 12.4 · 32768 ctx

    179.71 tok/s

    Decode

    772.31 tok/s

    Prefill

    1.05 s

    TTFT

    11.17 GB

    VRAM

    —

    MTP

    394.8 W

    Power draw

    L2 batch seed 2026-10-22: vLLM on hw_id=1 running model_id=95 at IQ2_XS