Arao AI
Back to search results

Qwen3.8-9B · Q4_K_M

Start a discussion
AMD Ryzen AI Max+ 395128GBllama.cpp v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_M) on AMD Ryzen AI Max+ 395 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

26.52 tok/s

Decode

Decode speed

94.42 tok/s

Prefill

Prefill speed

0.62 s

TTFT

Time to first token

17.6 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_M (current)Decode 26.52 · Prefill 94.42 ·
  2. vLLM · IQ2_M Decode 42.37 · Prefill 221.74 ·
  3. vLLM · Q6_K Decode 24.65 · Prefill 111.72 ·
  4. llama.cpp · IQ2_M Decode 125.51 · Prefill 634.19 ·
  5. llama.cpp · IQ3_S Decode 115.85 · Prefill 489.76 ·
  6. vLLM · Q5_K_M Decode 82.89 · Prefill 274.27 ·
  7. vLLM · IQ2_XS Decode 145.04 · Prefill 523.91 ·
  8. vLLM · Q3_K_L Decode 107.95 · Prefill 386.71 ·
  9. Strata · IQ3_XS Decode 164.91 · Prefill 583.87 ·
  10. Strata · Q5_K_S Decode 114.19 · Prefill 509.48 ·

Core figures

Decode (avg)
26.52 tok/s
Prefill (avg)
94.42 tok/s
TTFT (avg)
0.62 s
VRAM (avg)
17.6 GB
MTP acceptance rate
—
TTFB
0.21 GB
Power draw
54.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.44
Context length
8192 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

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)
17.6 GB
OS
Windows 11 23H2
Driver
amdgpu 6.12
CUDA
12.6
Power draw
54.6 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.44 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx

    26.52 tok/s

    Decode

    94.42 tok/s

    Prefill

    0.62 s

    TTFT

    17.6 GB

    VRAM

    —

    MTP

    54.6 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=24 running model_id=52 at Q4_K_M