Arao AI
Back to search results

Qwen3-1.7B · Q3_K_L

Start a discussion
AMD Radeon RX 907016GBllama.cpp v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_L) on AMD Radeon RX 9070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

168.28 tok/s

Decode

Decode speed

901.02 tok/s

Prefill

Prefill speed

2.16 s

TTFT

Time to first token

4.67 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ1_S Decode 251.73 · Prefill 1075.85 ·
  2. llama.cpp · Q3_K_L (current)Decode 168.28 · Prefill 901.02 ·
  3. Strata · IQ3_XS Decode 263.09 · Prefill 972.27 ·
  4. Strata · Q5_K_M Decode 186.72 · Prefill 727.73 ·

Core figures

Decode (avg)
168.28 tok/s
Prefill (avg)
901.02 tok/s
TTFT (avg)
2.16 s
VRAM (avg)
4.67 GB
MTP acceptance rate
—
TTFB
1.35 GB
Power draw
279.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q3_K_L
Framework
llama.cpp
Version
v0.49
Context length
32768 tokens
Batch size
256
GPU layers
28
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
AMD Radeon RX 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
4.67 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
279.5 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.49 · Ubuntu 22.04 · CUDA N/A · 32768 ctx

    168.28 tok/s

    Decode

    901.02 tok/s

    Prefill

    2.16 s

    TTFT

    4.67 GB

    VRAM

    —

    MTP

    279.5 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=21 running model_id=55 at Q3_K_L