Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q4_K_S

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBllama.cpp v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q4_K_S) on NVIDIA RTX 4060 Ti 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

221.58 tok/s

Decode

Decode speed

758 tok/s

Prefill

Prefill speed

0.29 s

TTFT

Time to first token

3.09 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_S (current)Decode 221.58 · Prefill 758 ·
  2. vLLM · IQ4_XS Decode 223.15 · Prefill 875.24 ·

Core figures

Decode (avg)
221.58 tok/s
Prefill (avg)
758 tok/s
TTFT (avg)
0.29 s
VRAM (avg)
3.09 GB
MTP acceptance rate
—
TTFB
1.77 GB
Power draw
369.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.34
Context length
8192 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4060 Ti 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
3.09 GB
OS
Ubuntu 24.04
Driver
555.85
CUDA
12.8
Power draw
369.4 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.34 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    221.58 tok/s

    Decode

    758 tok/s

    Prefill

    0.29 s

    TTFT

    3.09 GB

    VRAM

    —

    MTP

    369.4 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=3 running model_id=62 at Q4_K_S