Arao AI
Back to search results

elephant-1 · Q4_K_S

Start a discussion
NVIDIA RTX 509032GBllama.cpp v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of elephant-1 (Q4_K_S) on NVIDIA RTX 5090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

219.01 tok/s

Decode

Decode speed

766.77 tok/s

Prefill

Prefill speed

0.6 s

TTFT

Time to first token

16.84 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 · Q4_K_S (current)Decode 219.01 · Prefill 766.77 ·
  2. Ollama · Q5_K_S Decode 174.79 · Prefill 860.94 ·
  3. Ollama · Q8_0 Decode 138.97 · Prefill 570.96 ·

Core figures

Decode (avg)
219.01 tok/s
Prefill (avg)
766.77 tok/s
TTFT (avg)
0.6 s
VRAM (avg)
16.84 GB
MTP acceptance rate
—
TTFB
1.75 GB
Power draw
353.5 W

Configuration

Member-level fields are taken from the most recent run

Model
elephant-1
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.54
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 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
16.84 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
12.8
Power draw
353.5 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

    v0.54 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx

    219.01 tok/s

    Decode

    766.77 tok/s

    Prefill

    0.6 s

    TTFT

    16.84 GB

    VRAM

    —

    MTP

    353.5 W

    Power draw

    L2 batch seed 2026-10-22: llama.cpp on hw_id=13 running model_id=95 at Q4_K_S