Arao AI
Back to search results

Qwen3.5-0.8B · IQ3_S

Start a discussion
NVIDIA RTX 4070 Ti12GBvLLM v0.52L2 Cross-framework verified

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

341.56 tok/s

Decode

Decode speed

1,371.63 tok/s

Prefill

Prefill speed

0.94 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

Today

Last verified

Performance

  1. llama.cpp · IQ4_XS Decode 272.81 · Prefill 1057.01 ·
  2. vLLM · IQ3_S (current)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)
341.56 tok/s
Prefill (avg)
1,371.63 tok/s
TTFT (avg)
0.94 s
VRAM (avg)
3.21 GB
MTP acceptance rate
—
TTFB
2.73 GB
Power draw
285.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ3_S
Framework
vLLM
Version
v0.52
Context length
4096 tokens
Batch size
16
GPU layers
999
Flash Attention
Off

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)
3.21 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
13.0
Power draw
285.1 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

    v0.52 · Ubuntu 24.04 · CUDA 13.0 · 4096 ctx

    341.56 tok/s

    Decode

    1,371.63 tok/s

    Prefill

    0.94 s

    TTFT

    3.21 GB

    VRAM

    —

    MTP

    285.1 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=42 running model_id=51 at IQ3_S