Arao AI
Back to search results

Qwen3-8B · IQ3_XS

Start a discussion
NVIDIA RTX 4070 Ti12GBStrata v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ3_XS) on NVIDIA RTX 4070 Ti with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

173.97 tok/s

Decode

Decode speed

939.34 tok/s

Prefill

Prefill speed

1.44 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

Today

Last verified

Performance

  1. vLLM · Q3_K_S Decode 137.13 · Prefill 568.71 ·
  2. Strata · IQ3_XS (current)Decode 173.97 · Prefill 939.34 ·

Core figures

Decode (avg)
173.97 tok/s
Prefill (avg)
939.34 tok/s
TTFT (avg)
1.44 s
VRAM (avg)
11.4 GB
MTP acceptance rate
0.48
TTFB
1.39 GB
Power draw
299.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ3_XS
Framework
Strata
Version
v0.38
Context length
8192 tokens
Batch size
256
GPU layers
15
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
Windows 11 24H2
Driver
572.83
CUDA
13.0
Power draw
299.1 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

    v0.38 · Windows 11 24H2 · CUDA 13.0 · 8192 ctx

    173.97 tok/s

    Decode

    939.34 tok/s

    Prefill

    1.44 s

    TTFT

    11.4 GB

    VRAM

    0.48

    MTP

    299.1 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=42 running model_id=53 at IQ3_XS