Arao AI
Back to search results

Qwen3-Coder-Next · Q8_0

Start a discussion
AMD Strix Point (Radeon 890M)vLLM v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q8_0) on AMD Strix Point (Radeon 890M) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

38.46 tok/s

Decode

Decode speed

182.92 tok/s

Prefill

Prefill speed

2 s

TTFT

Time to first token

1.05 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · IQ1_S Decode 79.93 · Prefill 394.12 ·
  2. vLLM · Q8_0 (current)Decode 38.46 · Prefill 182.92 ·
  3. Ollama · Q5_K_M Decode 41.64 · Prefill 184.88 ·

Core figures

Decode (avg)
38.46 tok/s
Prefill (avg)
182.92 tok/s
TTFT (avg)
2 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.31 GB
Power draw
65.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
Q8_0
Framework
vLLM
Version
v0.52
Context length
16384 tokens
Batch size
32
GPU layers
999
Flash Attention
On

Hardware

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

GPU
AMD Strix Point (Radeon 890M)
Measured VRAM (avg)
1.05 GB
OS
macOS 15.0
Driver
570.86
CUDA
N/A
Power draw
65.2 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

    v0.52 · macOS 15.0 · CUDA N/A · 16384 ctx

    38.46 tok/s

    Decode

    182.92 tok/s

    Prefill

    2 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    65.2 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=89 running model_id=58 at Q8_0