Arao AI
Back to search results

Qwen3-4B · Q8_0

Start a discussion
NVIDIA RTX 4070 Ti12GBvLLM v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (Q8_0) on NVIDIA RTX 4070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

66.34 tok/s

Decode

Decode speed

241.62 tok/s

Prefill

Prefill speed

2.04 s

TTFT

Time to first token

11.4 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 · Q3_K_L Decode 107.42 · Prefill 453.38 ·
  2. llama.cpp · Q4_K_M Decode 104 · Prefill 443.35 ·
  3. vLLM · Q8_0 (current)Decode 66.34 · Prefill 241.62 ·

Core figures

Decode (avg)
66.34 tok/s
Prefill (avg)
241.62 tok/s
TTFT (avg)
2.04 s
VRAM (avg)
11.4 GB
MTP acceptance rate
—
TTFB
0.53 GB
Power draw
240.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
Q8_0
Framework
vLLM
Version
v0.51
Context length
16384 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 4070 Ti
Nominal VRAM
12 GB
Measured VRAM (avg)
11.4 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
12.4
Power draw
240.5 W

Sources & evidence

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

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

    v0.51 · Ubuntu 24.04 · CUDA 12.4 · 16384 ctx

    66.34 tok/s

    Decode

    241.62 tok/s

    Prefill

    2.04 s

    TTFT

    11.4 GB

    VRAM

    —

    MTP

    240.5 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=42 running model_id=54 at Q8_0