Arao AI
Back to search results

Qwen3-Coder-Next · Q3_K_L

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

This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q3_K_L) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

131.46 tok/s

Decode

Decode speed

705.73 tok/s

Prefill

Prefill speed

1.45 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 (current)Decode 131.46 · Prefill 705.73 ·
  2. Ollama · Q4_K_S 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)
131.46 tok/s
Prefill (avg)
705.73 tok/s
TTFT (avg)
1.45 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
1.05 GB
Power draw
158.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
Q3_K_L
Framework
Ollama
Version
v0.45
Context length
16384 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

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
Windows 11 23H2
Driver
565.57
CUDA
12.6
Power draw
158.6 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 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx

    131.46 tok/s

    Decode

    705.73 tok/s

    Prefill

    1.45 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    158.6 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=54 running model_id=58 at Q3_K_L