Arao AI
Back to search results

elephant-1 · Q8_0

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of elephant-1 (Q8_0) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

19.62 tok/s

Decode

Decode speed

103.78 tok/s

Prefill

Prefill speed

2.34 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

13 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_L Decode 32.72 · Prefill 137.17 ·
  2. vLLM · Q6_K Decode 22.65 · Prefill 118.27 ·
  3. vLLM · Q8_0 (current)Decode 19.62 · Prefill 103.78 ·

Core figures

Decode (avg)
19.62 tok/s
Prefill (avg)
103.78 tok/s
TTFT (avg)
2.34 s
VRAM (avg)
23.84 GB
MTP acceptance rate
—
TTFB
0.16 GB
Power draw
45.4 W

Configuration

Member-level fields are taken from the most recent run

Model
elephant-1
Quantization
Q8_0
Framework
vLLM
Version
v0.30
Context length
8192 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
AMD Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
23.84 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.12
CUDA
12.8
Power draw
45.4 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

    v0.30 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    19.62 tok/s

    Decode

    103.78 tok/s

    Prefill

    2.34 s

    TTFT

    23.84 GB

    VRAM

    —

    MTP

    45.4 W

    Power draw

    L2 batch seed 2026-10-22: vLLM on hw_id=24 running model_id=95 at Q8_0