Arao AI
Back to search results

Llama-3.1-8B-Instruct · IQ3_XS

Start a discussion
NVIDIA RTX 508016GBStrata v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ3_XS) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

308.04 tok/s

Decode

Decode speed

1,362.37 tok/s

Prefill

Prefill speed

1.39 s

TTFT

Time to first token

12.52 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 Decode 224.27 · Prefill 989.89 ·
  2. Strata · IQ3_XS (current)Decode 308.04 · Prefill 1362.37 ·
  3. Strata · Q3_K_S Decode 323.81 · Prefill 1737.95 ·

Core figures

Decode (avg)
308.04 tok/s
Prefill (avg)
1,362.37 tok/s
TTFT (avg)
1.39 s
VRAM (avg)
12.52 GB
MTP acceptance rate
0.47
TTFB
2.46 GB
Power draw
314.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
IQ3_XS
Framework
Strata
Version
v0.30
Context length
8192 tokens
Batch size
1024
GPU layers
12
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
12.52 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
13.0
Power draw
314.4 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

    v0.30 · Ubuntu 22.04 · CUDA 13.0 · 8192 ctx

    308.04 tok/s

    Decode

    1,362.37 tok/s

    Prefill

    1.39 s

    TTFT

    12.52 GB

    VRAM

    0.47

    MTP

    314.4 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=14 running model_id=68 at IQ3_XS