Arao AI
Back to search results

Llama-3.1-8B-Instruct · IQ4_XS

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBStrata v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ4_XS) on NVIDIA RTX 4060 Ti 16GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

154.65 tok/s

Decode

Decode speed

522.45 tok/s

Prefill

Prefill speed

1.54 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 · Q3_K_L Decode 118.42 · Prefill 384.95 ·
  2. Strata · IQ4_XS (current)Decode 154.65 · Prefill 522.45 ·

Core figures

Decode (avg)
154.65 tok/s
Prefill (avg)
522.45 tok/s
TTFT (avg)
1.54 s
VRAM (avg)
14.53 GB
MTP acceptance rate
0.73
TTFB
1.24 GB
Power draw
163.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
IQ4_XS
Framework
Strata
Version
v0.35
Context length
32768 tokens
Batch size
256
GPU layers
5
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4060 Ti 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
14.53 GB
OS
Windows 11 23H2
Driver
572.83
CUDA
12.6
Power draw
163.1 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

    v0.35 · Windows 11 23H2 · CUDA 12.6 · 32768 ctx

    154.65 tok/s

    Decode

    522.45 tok/s

    Prefill

    1.54 s

    TTFT

    14.53 GB

    VRAM

    0.73

    MTP

    163.1 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=3 running model_id=68 at IQ4_XS