Arao AI
Back to search results

Qwen3-1.7B · Q3_K_L

Start a discussion
AMD Radeon RX 7800 XT16GBStrata v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_L) on AMD Radeon RX 7800 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

238.01 tok/s

Decode

Decode speed

1,294.15 tok/s

Prefill

Prefill speed

1.97 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. Strata · IQ3_XS Decode 256.05 · Prefill 1389.06 ·
  2. Strata · Q3_K_L (current)Decode 238.01 · Prefill 1294.15 ·

Core figures

Decode (avg)
238.01 tok/s
Prefill (avg)
1,294.15 tok/s
TTFT (avg)
1.97 s
VRAM (avg)
4.67 GB
MTP acceptance rate
0.75
TTFB
1.9 GB
Power draw
241.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q3_K_L
Framework
Strata
Version
v0.44
Context length
4096 tokens
Batch size
256
GPU layers
5
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 7800 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
4.67 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
241.8 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

    v0.44 · Ubuntu 22.04 · CUDA N/A · 4096 ctx

    238.01 tok/s

    Decode

    1,294.15 tok/s

    Prefill

    1.97 s

    TTFT

    4.67 GB

    VRAM

    0.75

    MTP

    241.8 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=31 running model_id=55 at Q3_K_L