Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q3_K_S

Start a discussion
NVIDIA RTX 508016GBStrata v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q3_K_S) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

323.81 tok/s

Decode

Decode speed

1,737.95 tok/s

Prefill

Prefill speed

0.97 s

TTFT

Time to first token

13.02 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 Decode 308.04 · Prefill 1362.37 ·
  3. Strata · Q3_K_S (current)Decode 323.81 · Prefill 1737.95 ·

Core figures

Decode (avg)
323.81 tok/s
Prefill (avg)
1,737.95 tok/s
TTFT (avg)
0.97 s
VRAM (avg)
13.02 GB
MTP acceptance rate
0.73
TTFB
2.59 GB
Power draw
262.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q3_K_S
Framework
Strata
Version
v0.49
Context length
32768 tokens
Batch size
512
GPU layers
15
Flash Attention
Off

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)
13.02 GB
OS
Windows 11 24H2
Driver
572.83
CUDA
12.6
Power draw
262.4 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

    v0.49 · Windows 11 24H2 · CUDA 12.6 · 32768 ctx

    323.81 tok/s

    Decode

    1,737.95 tok/s

    Prefill

    0.97 s

    TTFT

    13.02 GB

    VRAM

    0.73

    MTP

    262.4 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=14 running model_id=68 at Q3_K_S