Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q2_K

Start a discussion
NVIDIA RTX 5070 Ti16GBvLLM v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q2_K) on NVIDIA RTX 5070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

134.24 tok/s

Decode

Decode speed

721.19 tok/s

Prefill

Prefill speed

1.93 s

TTFT

Time to first token

11.34 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 Decode 108.27 · Prefill 466.84 ·
  2. vLLM · IQ3_S Decode 128.33 · Prefill 495.87 ·
  3. vLLM · Q2_K (current)Decode 134.24 · Prefill 721.19 ·

Core figures

Decode (avg)
134.24 tok/s
Prefill (avg)
721.19 tok/s
TTFT (avg)
1.93 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
1.07 GB
Power draw
254 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q2_K
Framework
vLLM
Version
v0.37
Context length
4096 tokens
Batch size
32
GPU layers
999
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)
11.34 GB
OS
Windows 11 24H2
Driver
570.86
CUDA
12.6
Power draw
254 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

    v0.37 · Windows 11 24H2 · CUDA 12.6 · 4096 ctx

    134.24 tok/s

    Decode

    721.19 tok/s

    Prefill

    1.93 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    254 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=17 running model_id=68 at Q2_K