Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q3_K_S

Start a discussion
NVIDIA RTX 408016GBStrata v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q3_K_S) on NVIDIA RTX 4080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

388.23 tok/s

Decode

Decode speed

2,020.82 tok/s

Prefill

Prefill speed

1.23 s

TTFT

Time to first token

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

Core figures

Decode (avg)
388.23 tok/s
Prefill (avg)
2,020.82 tok/s
TTFT (avg)
1.23 s
VRAM (avg)
2.92 GB
MTP acceptance rate
0.78
TTFB
3.11 GB
Power draw
288 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q3_K_S
Framework
Strata
Version
v0.38
Context length
8192 tokens
Batch size
256
GPU layers
5
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)
2.92 GB
OS
Windows 11 23H2
Driver
555.85
CUDA
12.4
Power draw
288 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

    v0.38 · Windows 11 23H2 · CUDA 12.4 · 8192 ctx

    388.23 tok/s

    Decode

    2,020.82 tok/s

    Prefill

    1.23 s

    TTFT

    2.92 GB

    VRAM

    0.78

    MTP

    288 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=41 running model_id=62 at Q3_K_S