Arao AI
Back to search results

Qwen3-1.7B · Q4_K_S

Start a discussion
NVIDIA DGX Spark128GBStrata v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_S) on NVIDIA DGX Spark with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

375.7 tok/s

Decode

Decode speed

1,600.4 tok/s

Prefill

Prefill speed

0.18 s

TTFT

Time to first token

4.88 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 · Q2_K Decode 374.76 · Prefill 1672.78 ·
  2. vLLM · Q5_K_M Decode 240.21 · Prefill 1012.49 ·
  3. Strata · IQ3_XS Decode 315.95 · Prefill 1231.57 ·
  4. Strata · Q4_K_S (current)Decode 375.7 · Prefill 1600.4 ·
  5. llama.cpp · Q6_K Decode 210 · Prefill 1074.66 ·
  6. vLLM · Q3_K_M Decode 331.74 · Prefill 1116.84 ·

Core figures

Decode (avg)
375.7 tok/s
Prefill (avg)
1,600.4 tok/s
TTFT (avg)
0.18 s
VRAM (avg)
4.88 GB
MTP acceptance rate
0.77
TTFB
3.01 GB
Power draw
187.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q4_K_S
Framework
Strata
Version
v0.26
Context length
16384 tokens
Batch size
1024
GPU layers
12
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)
4.88 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.4
Power draw
187.4 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

    v0.26 · Ubuntu 22.04 · CUDA 12.4 · 16384 ctx

    375.7 tok/s

    Decode

    1,600.4 tok/s

    Prefill

    0.18 s

    TTFT

    4.88 GB

    VRAM

    0.77

    MTP

    187.4 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=54 running model_id=55 at Q4_K_S