Arao AI
Back to search results

Qwen3.5-4B · Q3_K_M

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBOllama v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_M) on NVIDIA RTX 4060 Ti 16GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

144.59 tok/s

Decode

Decode speed

690.26 tok/s

Prefill

Prefill speed

0.85 s

TTFT

Time to first token

7.81 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 Decode 147.52 · Prefill 627.05 ·
  2. Ollama · Q3_K_M (current)Decode 144.59 · Prefill 690.26 ·
  3. Strata · Q2_K Decode 195.73 · Prefill 812.84 ·

Core figures

Decode (avg)
144.59 tok/s
Prefill (avg)
690.26 tok/s
TTFT (avg)
0.85 s
VRAM (avg)
7.81 GB
MTP acceptance rate
—
TTFB
1.16 GB
Power draw
179.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q3_K_M
Framework
Ollama
Version
v0.32
Context length
16384 tokens
Batch size
512
GPU layers
28
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)
7.81 GB
OS
Windows 11 24H2
Driver
565.57
CUDA
12.8
Power draw
179.3 W

Sources & evidence

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

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

    v0.32 · Windows 11 24H2 · CUDA 12.8 · 16384 ctx

    144.59 tok/s

    Decode

    690.26 tok/s

    Prefill

    0.85 s

    TTFT

    7.81 GB

    VRAM

    —

    MTP

    179.3 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=3 running model_id=48 at Q3_K_M