Arao AI
Back to search results

Qwen3.5-0.8B · IQ4_XS

Start a discussion
AMD Ryzen AI Max+ 395128GBllama.cpp v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ4_XS) on AMD Ryzen AI Max+ 395 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

273.83 tok/s

Decode

Decode speed

1,312.19 tok/s

Prefill

Prefill speed

0.64 s

TTFT

Time to first token

3.34 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ4_XS (current)Decode 273.83 · Prefill 1312.19 ·
  2. llama.cpp · Q5_K_M Decode 197.9 · Prefill 695.65 ·
  3. Ollama · Q4_K_M Decode 220.93 · Prefill 741.5 ·
  4. Ollama · Q8_0 Decode 163.22 · Prefill 720.03 ·
  5. llama.cpp · IQ1_S Decode 380.54 · Prefill 1677.44 ·
  6. llama.cpp · IQ2_XS Decode 354.37 · Prefill 1453.65 ·

Core figures

Decode (avg)
273.83 tok/s
Prefill (avg)
1,312.19 tok/s
TTFT (avg)
0.64 s
VRAM (avg)
3.34 GB
MTP acceptance rate
—
TTFB
2.19 GB
Power draw
81.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ4_XS
Framework
llama.cpp
Version
v0.36
Context length
2048 tokens
Batch size
512
GPU layers
33
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)
3.34 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
N/A
Power draw
81.1 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.36 · Ubuntu 24.04 · CUDA N/A · 2048 ctx

    273.83 tok/s

    Decode

    1,312.19 tok/s

    Prefill

    0.64 s

    TTFT

    3.34 GB

    VRAM

    —

    MTP

    81.1 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=24 running model_id=51 at IQ4_XS