Arao AI
Back to search results

Qwen3.5-0.8B · IQ4_XS

Start a discussion
NVIDIA RTX 4070 Ti12GBllama.cpp v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ4_XS) on NVIDIA RTX 4070 Ti with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

272.81 tok/s

Decode

Decode speed

1,057.01 tok/s

Prefill

Prefill speed

0.96 s

TTFT

Time to first token

3.34 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 272.81 · Prefill 1057.01 ·
  2. vLLM · IQ3_S Decode 341.56 · Prefill 1371.63 ·
  3. vLLM · Q8_0 Decode 188.8 · Prefill 665.28 ·
  4. llama.cpp · IQ3_XS Decode 242.17 · Prefill 959.61 ·
  5. llama.cpp · Q3_K_S Decode 230.59 · Prefill 747.57 ·

Core figures

Decode (avg)
272.81 tok/s
Prefill (avg)
1,057.01 tok/s
TTFT (avg)
0.96 s
VRAM (avg)
3.34 GB
MTP acceptance rate
—
TTFB
2.18 GB
Power draw
228.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ4_XS
Framework
llama.cpp
Version
v0.32
Context length
4096 tokens
Batch size
512
GPU layers
99
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 Ti
Nominal VRAM
12 GB
Measured VRAM (avg)
3.34 GB
OS
Windows 11 24H2
Driver
565.57
CUDA
12.8
Power draw
228.5 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

    v0.32 · Windows 11 24H2 · CUDA 12.8 · 4096 ctx

    272.81 tok/s

    Decode

    1,057.01 tok/s

    Prefill

    0.96 s

    TTFT

    3.34 GB

    VRAM

    —

    MTP

    228.5 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=42 running model_id=51 at IQ4_XS