Arao AI
Back to search results

Qwen3-8B · IQ4_XS

Start a discussion
NVIDIA RTX 408016GBStrata v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ4_XS) on NVIDIA RTX 4080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

189.04 tok/s

Decode

Decode speed

930.37 tok/s

Prefill

Prefill speed

0.46 s

TTFT

Time to first token

14.53 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · IQ3_S Decode 137.8 · Prefill 706.29 ·
  2. Ollama · IQ3_XS Decode 158.58 · Prefill 727 ·
  3. Strata · IQ3_S Decode 234.8 · Prefill 1203.48 ·
  4. Strata · IQ4_XS (current)Decode 189.04 · Prefill 930.37 ·
  5. llama.cpp · IQ1_S Decode 141.07 · Prefill 456.51 ·
  6. llama.cpp · IQ3_S Decode 105.08 · Prefill 472.34 ·
  7. vLLM · IQ1_S Decode 150.38 · Prefill 727.2 ·

Core figures

Decode (avg)
189.04 tok/s
Prefill (avg)
930.37 tok/s
TTFT (avg)
0.46 s
VRAM (avg)
14.53 GB
MTP acceptance rate
0.62
TTFB
1.51 GB
Power draw
212.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ4_XS
Framework
Strata
Version
v0.36
Context length
8192 tokens
Batch size
512
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 4080
Nominal VRAM
16 GB
Measured VRAM (avg)
14.53 GB
OS
Windows 11 24H2
Driver
570.86
CUDA
12.8
Power draw
212.6 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

    v0.36 · Windows 11 24H2 · CUDA 12.8 · 8192 ctx

    189.04 tok/s

    Decode

    930.37 tok/s

    Prefill

    0.46 s

    TTFT

    14.53 GB

    VRAM

    0.62

    MTP

    212.6 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=41 running model_id=53 at IQ4_XS