Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q4_K_S

Start a discussion
NVIDIA RTX 5070 Ti16GBllama.cpp v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q4_K_S) on NVIDIA RTX 5070 Ti with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

108.27 tok/s

Decode

Decode speed

466.84 tok/s

Prefill

Prefill speed

0.92 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q4_K_S (current)Decode 108.27 · Prefill 466.84 ·
  2. vLLM · IQ3_S Decode 128.33 · Prefill 495.87 ·
  3. vLLM · Q2_K Decode 134.24 · Prefill 721.19 ·

Core figures

Decode (avg)
108.27 tok/s
Prefill (avg)
466.84 tok/s
TTFT (avg)
0.92 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.87 GB
Power draw
205.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.53
Context length
2048 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5070 Ti
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Windows 11 24H2
Driver
560.94
CUDA
12.4
Power draw
205.8 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

    v0.53 · Windows 11 24H2 · CUDA 12.4 · 2048 ctx

    108.27 tok/s

    Decode

    466.84 tok/s

    Prefill

    0.92 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    205.8 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=17 running model_id=68 at Q4_K_S