Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q3_K_L

Start a discussion
NVIDIA RTX 4080 Super16GBvLLM v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q3_K_L) on NVIDIA RTX 4080 Super with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

177.01 tok/s

Decode

Decode speed

908.47 tok/s

Prefill

Prefill speed

1.17 s

TTFT

Time to first token

14.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ2_M Decode 224.52 · Prefill 1147.46 ·
  2. vLLM · Q3_K_L (current)Decode 177.01 · Prefill 908.47 ·
  3. Ollama · IQ2_M Decode 204.79 · Prefill 1109.54 ·

Core figures

Decode (avg)
177.01 tok/s
Prefill (avg)
908.47 tok/s
TTFT (avg)
1.17 s
VRAM (avg)
14.2 GB
MTP acceptance rate
—
TTFB
1.42 GB
Power draw
286.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q3_K_L
Framework
vLLM
Version
v0.51
Context length
32768 tokens
Batch size
16
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 4080 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
14.2 GB
OS
Windows 11 24H2
Driver
565.57
CUDA
12.4
Power draw
286.3 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

    v0.51 · Windows 11 24H2 · CUDA 12.4 · 32768 ctx

    177.01 tok/s

    Decode

    908.47 tok/s

    Prefill

    1.17 s

    TTFT

    14.2 GB

    VRAM

    —

    MTP

    286.3 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=20 running model_id=68 at Q3_K_L