Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · Q3_K_L

Start a discussion
NVIDIA DGX Spark128GBOllama v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q3_K_L) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

191.76 tok/s

Decode

Decode speed

876.65 tok/s

Prefill

Prefill speed

2.48 s

TTFT

Time to first token

8.15 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · IQ1_S Decode 291.5 · Prefill 1360.04 ·
  2. vLLM · Q5_K_M Decode 151.71 · Prefill 832.95 ·
  3. Strata · Q5_K_M Decode 220.61 · Prefill 780.86 ·
  4. Ollama · Q3_K_L (current)Decode 191.76 · Prefill 876.65 ·
  5. Ollama · Q5_K_S Decode 148.12 · Prefill 634.82 ·

Core figures

Decode (avg)
191.76 tok/s
Prefill (avg)
876.65 tok/s
TTFT (avg)
2.48 s
VRAM (avg)
8.15 GB
MTP acceptance rate
—
TTFB
1.53 GB
Power draw
257.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
Q3_K_L
Framework
Ollama
Version
v0.22
Context length
32768 tokens
Batch size
256
GPU layers
99
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)
8.15 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.8
Power draw
257.7 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

    v0.22 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    191.76 tok/s

    Decode

    876.65 tok/s

    Prefill

    2.48 s

    TTFT

    8.15 GB

    VRAM

    —

    MTP

    257.7 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=54 running model_id=57 at Q3_K_L