Arao AI
Back to search results

Qwen3.5-4B · IQ4_XS

Start a discussion
NVIDIA RTX 508016GBllama.cpp v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ4_XS) on NVIDIA RTX 5080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

133.14 tok/s

Decode

Decode speed

731.5 tok/s

Prefill

Prefill speed

1.47 s

TTFT

Time to first token

8.32 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ4_XS (current)Decode 133.14 · Prefill 731.5 ·
  2. Strata · Q3_K_M Decode 231.73 · Prefill 785.76 ·

Core figures

Decode (avg)
133.14 tok/s
Prefill (avg)
731.5 tok/s
TTFT (avg)
1.47 s
VRAM (avg)
8.32 GB
MTP acceptance rate
—
TTFB
1.07 GB
Power draw
268.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ4_XS
Framework
llama.cpp
Version
v0.48
Context length
8192 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 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
8.32 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.8
Power draw
268.4 W

Sources & evidence

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

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

    v0.48 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx

    133.14 tok/s

    Decode

    731.5 tok/s

    Prefill

    1.47 s

    TTFT

    8.32 GB

    VRAM

    —

    MTP

    268.4 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=14 running model_id=48 at IQ4_XS