Arao AI
Back to search results

Qwen3.5-0.8B · IQ3_S

Start a discussion
NVIDIA RTX 407012GBllama.cpp v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_S) on NVIDIA RTX 4070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

227.1 tok/s

Decode

Decode speed

1,033.86 tok/s

Prefill

Prefill speed

2.27 s

TTFT

Time to first token

3.21 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ3_S (current)Decode 227.1 · Prefill 1033.86 ·

Core figures

Decode (avg)
227.1 tok/s
Prefill (avg)
1,033.86 tok/s
TTFT (avg)
2.27 s
VRAM (avg)
3.21 GB
MTP acceptance rate
—
TTFB
1.82 GB
Power draw
279.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ3_S
Framework
llama.cpp
Version
v0.38
Context length
16384 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 4070
Nominal VRAM
12 GB
Measured VRAM (avg)
3.21 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.8
Power draw
279.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.38 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx

    227.1 tok/s

    Decode

    1,033.86 tok/s

    Prefill

    2.27 s

    TTFT

    3.21 GB

    VRAM

    —

    MTP

    279.6 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=45 running model_id=51 at IQ3_S