Arao AI
Back to search results

Qwen3-1.7B · Q5_K_S

Start a discussion
2x AMD Strix Halollama.cpp v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q5_K_S) on 2x AMD Strix Halo with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

236.18 tok/s

Decode

Decode speed

1,075.25 tok/s

Prefill

Prefill speed

1.16 s

TTFT

Time to first token

5.31 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 · Q5_K_S (current)Decode 236.18 · Prefill 1075.25 ·
  2. Strata · Q5_K_M Decode 284.45 · Prefill 1280.23 ·
  3. Strata · Q5_K_S Decode 326.25 · Prefill 1416.72 ·

Core figures

Decode (avg)
236.18 tok/s
Prefill (avg)
1,075.25 tok/s
TTFT (avg)
1.16 s
VRAM (avg)
5.31 GB
MTP acceptance rate
—
TTFB
1.89 GB
Power draw
76.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.42
Context length
2048 tokens
Batch size
256
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
2x AMD Strix Halo
Measured VRAM (avg)
5.31 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
76.1 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

    v0.42 · Ubuntu 22.04 · CUDA N/A · 2048 ctx

    236.18 tok/s

    Decode

    1,075.25 tok/s

    Prefill

    1.16 s

    TTFT

    5.31 GB

    VRAM

    —

    MTP

    76.1 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=88 running model_id=55 at Q5_K_S