Arao AI
Back to search results

Llama-3-8B-Instruct · IQ2_XS

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

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (IQ2_XS) on NVIDIA RTX 4070 Ti with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

234.91 tok/s

Decode

Decode speed

843.49 tok/s

Prefill

Prefill speed

1.81 s

TTFT

Time to first token

10.16 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Strata · IQ2_XS (current)Decode 234.91 · Prefill 843.49 ·

Core figures

Decode (avg)
234.91 tok/s
Prefill (avg)
843.49 tok/s
TTFT (avg)
1.81 s
VRAM (avg)
10.16 GB
MTP acceptance rate
0.66
TTFB
1.88 GB
Power draw
230.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
IQ2_XS
Framework
Strata
Version
v0.38
Context length
4096 tokens
Batch size
1024
GPU layers
12
Flash Attention
Off

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)
10.16 GB
OS
Windows 11 24H2
Driver
572.83
CUDA
13.0
Power draw
230.9 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 · 4096 ctx

    234.91 tok/s

    Decode

    843.49 tok/s

    Prefill

    1.81 s

    TTFT

    10.16 GB

    VRAM

    0.66

    MTP

    230.9 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=42 running model_id=69 at IQ2_XS