Arao AI
Back to search results

elephant-1 · Q8_0

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

This page aggregates 1 real-world runs of elephant-1 (Q8_0) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

138.97 tok/s

Decode

Decode speed

570.96 tok/s

Prefill

Prefill speed

0.28 s

TTFT

Time to first token

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

Core figures

Decode (avg)
138.97 tok/s
Prefill (avg)
570.96 tok/s
TTFT (avg)
0.28 s
VRAM (avg)
23.84 GB
MTP acceptance rate
—
TTFB
1.11 GB
Power draw
379.5 W

Configuration

Member-level fields are taken from the most recent run

Model
elephant-1
Quantization
Q8_0
Framework
Ollama
Version
v0.54
Context length
8192 tokens
Batch size
256
GPU layers
20
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)
23.84 GB
OS
Windows 11 23H2
Driver
572.83
CUDA
12.8
Power draw
379.5 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 · Windows 11 23H2 · CUDA 12.8 · 8192 ctx

    138.97 tok/s

    Decode

    570.96 tok/s

    Prefill

    0.28 s

    TTFT

    23.84 GB

    VRAM

    —

    MTP

    379.5 W

    Power draw

    L2 batch seed 2026-10-22: Ollama on hw_id=13 running model_id=95 at Q8_0