Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_XS

Start a discussion
NVIDIA DGX Spark128GBOllama v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_XS) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

348.98 tok/s

Decode

Decode speed

1,689.57 tok/s

Prefill

Prefill speed

0.73 s

TTFT

Time to first token

2.91 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · IQ2_XS Decode 310.29 · Prefill 1000.44 ·
  2. Ollama · IQ2_XS (current)Decode 348.98 · Prefill 1689.57 ·
  3. Ollama · Q3_K_M Decode 387.92 · Prefill 1612.07 ·
  4. Ollama · IQ3_XS Decode 391.28 · Prefill 1950.82 ·
  5. Ollama · IQ4_XS Decode 338.64 · Prefill 1719.5 ·

Core figures

Decode (avg)
348.98 tok/s
Prefill (avg)
1,689.57 tok/s
TTFT (avg)
0.73 s
VRAM (avg)
2.91 GB
MTP acceptance rate
—
TTFB
2.79 GB
Power draw
251.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_XS
Framework
Ollama
Version
v0.33
Context length
2048 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)
2.91 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.4
Power draw
251.8 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

    v0.33 · Ubuntu 22.04 · CUDA 12.4 · 2048 ctx

    348.98 tok/s

    Decode

    1,689.57 tok/s

    Prefill

    0.73 s

    TTFT

    2.91 GB

    VRAM

    —

    MTP

    251.8 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=54 running model_id=51 at IQ2_XS