Arao AI
Back to search results

Qwen3.5-4B · IQ1_S

Start a discussion
NVIDIA RTX 5070 Ti16GBllama.cpp v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ1_S) on NVIDIA RTX 5070 Ti with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

182.74 tok/s

Decode

Decode speed

910.54 tok/s

Prefill

Prefill speed

2.11 s

TTFT

Time to first token

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

Core figures

Decode (avg)
182.74 tok/s
Prefill (avg)
910.54 tok/s
TTFT (avg)
2.11 s
VRAM (avg)
5.63 GB
MTP acceptance rate
—
TTFB
1.46 GB
Power draw
276.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.53
Context length
16384 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

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)
5.63 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.6
Power draw
276.7 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

    v0.53 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx

    182.74 tok/s

    Decode

    910.54 tok/s

    Prefill

    2.11 s

    TTFT

    5.63 GB

    VRAM

    —

    MTP

    276.7 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=17 running model_id=48 at IQ1_S