Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ1_S

Start a discussion
NVIDIA RTX 408016GBvLLM v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ1_S) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

305.89 tok/s

Decode

Decode speed

1,188.81 tok/s

Prefill

Prefill speed

2.38 s

TTFT

Time to first token

2.62 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 (current)Decode 305.89 · Prefill 1188.81 ·
  2. vLLM · Q3_K_S Decode 310.84 · Prefill 1177.49 ·
  3. Strata · Q3_K_S Decode 388.23 · Prefill 2020.82 ·

Core figures

Decode (avg)
305.89 tok/s
Prefill (avg)
1,188.81 tok/s
TTFT (avg)
2.38 s
VRAM (avg)
2.62 GB
MTP acceptance rate
—
TTFB
2.45 GB
Power draw
336.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ1_S
Framework
vLLM
Version
v0.39
Context length
4096 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 4080
Nominal VRAM
16 GB
Measured VRAM (avg)
2.62 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.4
Power draw
336.3 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 22.04 · CUDA 12.4 · 4096 ctx

    305.89 tok/s

    Decode

    1,188.81 tok/s

    Prefill

    2.38 s

    TTFT

    2.62 GB

    VRAM

    —

    MTP

    336.3 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=41 running model_id=62 at IQ1_S