Arao AI
Back to search results

Qwen3.8-9B · IQ4_XS

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBvLLM v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (IQ4_XS) on NVIDIA RTX 4060 Ti 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

104.81 tok/s

Decode

Decode speed

479.61 tok/s

Prefill

Prefill speed

0.19 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ4_XS (current)Decode 104.81 · Prefill 479.61 ·
  2. vLLM · Q3_K_M Decode 106.76 · Prefill 483.03 ·
  3. Strata · IQ2_XS Decode 182.07 · Prefill 797.96 ·
  4. vLLM · IQ2_M Decode 110.8 · Prefill 556.06 ·
  5. Ollama · Q4_K_M Decode 65.8 · Prefill 285.42 ·

Core figures

Decode (avg)
104.81 tok/s
Prefill (avg)
479.61 tok/s
TTFT (avg)
0.19 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.84 GB
Power draw
169.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
IQ4_XS
Framework
vLLM
Version
v0.51
Context length
8192 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 4060 Ti 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.8
Power draw
169.7 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

    v0.51 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    104.81 tok/s

    Decode

    479.61 tok/s

    Prefill

    0.19 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    169.7 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=3 running model_id=52 at IQ4_XS