Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ2_XS

Start a discussion
NVIDIA RTX 509032GBvLLM v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ2_XS) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

304.51 tok/s

Decode

Decode speed

1,432.77 tok/s

Prefill

Prefill speed

0.21 s

TTFT

Time to first token

2.71 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 (current)Decode 304.51 · Prefill 1432.77 ·
  2. vLLM · Q3_K_S Decode 322.2 · Prefill 1743.15 ·
  3. Strata · Q2_K Decode 350.56 · Prefill 1533.82 ·
  4. Strata · Q5_K_M Decode 291.92 · Prefill 1133.9 ·

Core figures

Decode (avg)
304.51 tok/s
Prefill (avg)
1,432.77 tok/s
TTFT (avg)
0.21 s
VRAM (avg)
2.71 GB
MTP acceptance rate
—
TTFB
2.44 GB
Power draw
381.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ2_XS
Framework
vLLM
Version
v0.48
Context length
32768 tokens
Batch size
16
GPU layers
999
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
2.71 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.8
Power draw
381.9 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

    v0.48 · Windows 11 23H2 · CUDA 12.8 · 32768 ctx

    304.51 tok/s

    Decode

    1,432.77 tok/s

    Prefill

    0.21 s

    TTFT

    2.71 GB

    VRAM

    —

    MTP

    381.9 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=13 running model_id=62 at IQ2_XS