Arao AI
Back to search results

Llama-3-8B-Instruct · Q3_K_S

Start a discussion
NVIDIA RTX 4080 Super16GBvLLM v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q3_K_S) on NVIDIA RTX 4080 Super with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

189.4 tok/s

Decode

Decode speed

632.63 tok/s

Prefill

Prefill speed

1.7 s

TTFT

Time to first token

13.02 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q3_K_S (current)Decode 189.4 · Prefill 632.63 ·
  2. Ollama · IQ1_S Decode 212.31 · Prefill 982.11 ·
  3. Ollama · IQ3_XS Decode 184.92 · Prefill 617.23 ·

Core figures

Decode (avg)
189.4 tok/s
Prefill (avg)
632.63 tok/s
TTFT (avg)
1.7 s
VRAM (avg)
13.02 GB
MTP acceptance rate
—
TTFB
1.52 GB
Power draw
253.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q3_K_S
Framework
vLLM
Version
v0.25
Context length
32768 tokens
Batch size
8
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)
13.02 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.8
Power draw
253.8 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

    v0.25 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    189.4 tok/s

    Decode

    632.63 tok/s

    Prefill

    1.7 s

    TTFT

    13.02 GB

    VRAM

    —

    MTP

    253.8 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=20 running model_id=69 at Q3_K_S