Arao AI
Back to search results

Qwen3-Coder-Next · Q3_K_S

Start a discussion
AMD Ryzen AI Max+ 395128GBOllama v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q3_K_S) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

98.59 tok/s

Decode

Decode speed

347.51 tok/s

Prefill

Prefill speed

1.24 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. llama.cpp · Q4_K_S Decode 90.68 · Prefill 349.79 ·
  2. Ollama · IQ2_M Decode 108.9 · Prefill 355.25 ·
  3. Ollama · Q3_K_S (current)Decode 98.59 · Prefill 347.51 ·

Core figures

Decode (avg)
98.59 tok/s
Prefill (avg)
347.51 tok/s
TTFT (avg)
1.24 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.79 GB
Power draw
105.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
Q3_K_S
Framework
Ollama
Version
v0.29
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
Off

Hardware

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

GPU
AMD Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
1.05 GB
OS
Ubuntu 22.04
Driver
560.94
CUDA
N/A
Power draw
105.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.29 · Ubuntu 22.04 · CUDA N/A · 4096 ctx

    98.59 tok/s

    Decode

    347.51 tok/s

    Prefill

    1.24 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    105.8 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=24 running model_id=58 at Q3_K_S