Arao AI
Back to search results

Qwen3.5-4B · IQ4_XS

Start a discussion
NVIDIA RTX 5070 Ti16GBvLLM v0.50L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ4_XS) on NVIDIA RTX 5070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

131.32 tok/s

Decode

Decode speed

455.29 tok/s

Prefill

Prefill speed

1.61 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 · IQ1_S Decode 182.74 · Prefill 910.54 ·
  2. vLLM · IQ4_XS (current)Decode 131.32 · Prefill 455.29 ·
  3. vLLM · Q4_K_M Decode 116.07 · Prefill 492.31 ·

Core figures

Decode (avg)
131.32 tok/s
Prefill (avg)
455.29 tok/s
TTFT (avg)
1.61 s
VRAM (avg)
8.32 GB
MTP acceptance rate
—
TTFB
1.05 GB
Power draw
205.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ4_XS
Framework
vLLM
Version
v0.50
Context length
32768 tokens
Batch size
32
GPU layers
999
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5070 Ti
Nominal VRAM
16 GB
Measured VRAM (avg)
8.32 GB
OS
Windows 11 24H2
Driver
565.57
CUDA
12.8
Power draw
205.5 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

    v0.50 · Windows 11 24H2 · CUDA 12.8 · 32768 ctx

    131.32 tok/s

    Decode

    455.29 tok/s

    Prefill

    1.61 s

    TTFT

    8.32 GB

    VRAM

    —

    MTP

    205.5 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=17 running model_id=48 at IQ4_XS