Arao AI
Back to search results

Qwen3.8-9B · Q3_K_L

Start a discussion
AMD Radeon RX 7800 XT16GBStrata v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_L) on AMD Radeon RX 7800 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

116.61 tok/s

Decode

Decode speed

394.73 tok/s

Prefill

Prefill speed

2.32 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · Q3_K_M Decode 81.38 · Prefill 413.01 ·
  2. Strata · Q3_K_L (current)Decode 116.61 · Prefill 394.73 ·

Core figures

Decode (avg)
116.61 tok/s
Prefill (avg)
394.73 tok/s
TTFT (avg)
2.32 s
VRAM (avg)
15.2 GB
MTP acceptance rate
0.67
TTFB
0.93 GB
Power draw
262.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q3_K_L
Framework
Strata
Version
v0.37
Context length
2048 tokens
Batch size
1024
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)
15.2 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
262.9 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

    v0.37 · Windows 11 23H2 · CUDA N/A · 2048 ctx

    116.61 tok/s

    Decode

    394.73 tok/s

    Prefill

    2.32 s

    TTFT

    15.2 GB

    VRAM

    0.67

    MTP

    262.9 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=31 running model_id=52 at Q3_K_L