Arao AI
Back to search results

elephant-1 · Q3_K_L

Start a discussion
AMD Ryzen AI Max+ 395128GBllama.cpp v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of elephant-1 (Q3_K_L) on AMD Ryzen AI Max+ 395 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

32.72 tok/s

Decode

Decode speed

137.17 tok/s

Prefill

Prefill speed

2.45 s

TTFT

Time to first token

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

Core figures

Decode (avg)
32.72 tok/s
Prefill (avg)
137.17 tok/s
TTFT (avg)
2.45 s
VRAM (avg)
15.71 GB
MTP acceptance rate
—
TTFB
0.26 GB
Power draw
52.8 W

Configuration

Member-level fields are taken from the most recent run

Model
elephant-1
Quantization
Q3_K_L
Framework
llama.cpp
Version
v0.51
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
AMD Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
15.71 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
12.4
Power draw
52.8 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

    v0.51 · Windows 11 23H2 · CUDA 12.4 · 2048 ctx

    32.72 tok/s

    Decode

    137.17 tok/s

    Prefill

    2.45 s

    TTFT

    15.71 GB

    VRAM

    —

    MTP

    52.8 W

    Power draw

    L2 batch seed 2026-10-22: llama.cpp on hw_id=24 running model_id=95 at Q3_K_L