Arao AI
Back to search results

Qwen3.5-4B · Q3_K_S

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBllama.cpp v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_S) on NVIDIA RTX 4060 Ti 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

147.52 tok/s

Decode

Decode speed

627.05 tok/s

Prefill

Prefill speed

2.22 s

TTFT

Time to first token

7.56 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q3_K_S (current)Decode 147.52 · Prefill 627.05 ·
  2. Ollama · Q3_K_M Decode 144.59 · Prefill 690.26 ·
  3. Strata · Q2_K Decode 195.73 · Prefill 812.84 ·

Core figures

Decode (avg)
147.52 tok/s
Prefill (avg)
627.05 tok/s
TTFT (avg)
2.22 s
VRAM (avg)
7.56 GB
MTP acceptance rate
—
TTFB
1.18 GB
Power draw
150.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q3_K_S
Framework
llama.cpp
Version
v0.40
Context length
32768 tokens
Batch size
512
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)
7.56 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
150.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.40 · Ubuntu 22.04 · CUDA 12.6 · 32768 ctx

    147.52 tok/s

    Decode

    627.05 tok/s

    Prefill

    2.22 s

    TTFT

    7.56 GB

    VRAM

    —

    MTP

    150.6 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=3 running model_id=48 at Q3_K_S