Arao AI
Back to search results

Qwen3.8-9B · IQ3_S

Start a discussion
NVIDIA RTX 5070 Ti16GBvLLM v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (IQ3_S) on NVIDIA RTX 5070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

103.59 tok/s

Decode

Decode speed

387.95 tok/s

Prefill

Prefill speed

1.29 s

TTFT

Time to first token

14.57 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ3_S (current)Decode 103.59 · Prefill 387.95 ·
  2. vLLM · Q3_K_M Decode 98.53 · Prefill 475.97 ·
  3. Ollama · IQ3_XS Decode 89.42 · Prefill 466.92 ·
  4. Ollama · Q2_K Decode 98.9 · Prefill 326.08 ·

Core figures

Decode (avg)
103.59 tok/s
Prefill (avg)
387.95 tok/s
TTFT (avg)
1.29 s
VRAM (avg)
14.57 GB
MTP acceptance rate
—
TTFB
0.83 GB
Power draw
277.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
IQ3_S
Framework
vLLM
Version
v0.27
Context length
2048 tokens
Batch size
8
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 5070 Ti
Nominal VRAM
16 GB
Measured VRAM (avg)
14.57 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.8
Power draw
277.9 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

    v0.27 · Ubuntu 22.04 · CUDA 12.8 · 2048 ctx

    103.59 tok/s

    Decode

    387.95 tok/s

    Prefill

    1.29 s

    TTFT

    14.57 GB

    VRAM

    —

    MTP

    277.9 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=17 running model_id=52 at IQ3_S