Arao AI
Back to search results

Qwen3-Coder-Next · Q4_K_S

Start a discussion
NVIDIA DGX Spark128GBOllama v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q4_K_S) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

128.78 tok/s

Decode

Decode speed

450.1 tok/s

Prefill

Prefill speed

0.98 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. Ollama · Q3_K_L Decode 131.46 · Prefill 705.73 ·
  2. Ollama · Q4_K_S (current)Decode 128.78 · Prefill 450.1 ·
  3. Strata · IQ2_M Decode 261.64 · Prefill 916.28 ·
  4. Strata · IQ2_XS Decode 259.54 · Prefill 1190.55 ·

Core figures

Decode (avg)
128.78 tok/s
Prefill (avg)
450.1 tok/s
TTFT (avg)
0.98 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
1.03 GB
Power draw
264.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
Q4_K_S
Framework
Ollama
Version
v0.45
Context length
2048 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

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

GPU
NVIDIA DGX Spark
Nominal VRAM
128 GB
Measured VRAM (avg)
1.05 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.8
Power draw
264.2 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

    v0.45 · Ubuntu 22.04 · CUDA 12.8 · 2048 ctx

    128.78 tok/s

    Decode

    450.1 tok/s

    Prefill

    0.98 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    264.2 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=54 running model_id=58 at Q4_K_S