Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · Q6_K

Start a discussion
NVIDIA DGX Spark128GBOllama v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q6_K) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

298.04 tok/s

Decode

Decode speed

1,558.09 tok/s

Prefill

Prefill speed

0.97 s

TTFT

Time to first token

3.15 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS Decode 344.66 · Prefill 1710.46 ·
  2. Strata · IQ2_XS Decode 295.77 · Prefill 1437.09 ·
  3. Strata · Q5_K_M Decode 294.11 · Prefill 1222.22 ·
  4. Ollama · IQ4_XS Decode 345.19 · Prefill 1510.37 ·
  5. Ollama · Q6_K (current)Decode 298.04 · Prefill 1558.09 ·

Core figures

Decode (avg)
298.04 tok/s
Prefill (avg)
1,558.09 tok/s
TTFT (avg)
0.97 s
VRAM (avg)
3.15 GB
MTP acceptance rate
—
TTFB
2.38 GB
Power draw
249.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
Q6_K
Framework
Ollama
Version
v0.39
Context length
2048 tokens
Batch size
512
GPU layers
28
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)
3.15 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.8
Power draw
249.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.39 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx

    298.04 tok/s

    Decode

    1,558.09 tok/s

    Prefill

    0.97 s

    TTFT

    3.15 GB

    VRAM

    —

    MTP

    249.8 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=54 running model_id=59 at Q6_K