Arao AI
Back to search results

Llama-3-8B-Instruct · Q5_K_S

Start a discussion
NVIDIA RTX 409024GBllama.cpp v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q5_K_S) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

118.71 tok/s

Decode

Decode speed

394.1 tok/s

Prefill

Prefill speed

0.47 s

TTFT

Time to first token

17.22 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q5_K_S (current)Decode 118.71 · Prefill 394.1 ·
  2. vLLM · IQ3_S Decode 177.41 · Prefill 791.84 ·
  3. vLLM · Q4_K_S Decode 157.4 · Prefill 646.64 ·
  4. llama.cpp · Q4_K_M Decode 146.97 · Prefill 902.58 ·
  5. llama.cpp · Q4_K_S Decode 134.4 · Prefill 594.59 ·
  6. Strata · Q2_K Decode 254.93 · Prefill 1284 ·
  7. llama.cpp · Q8_0 Decode 91.4 · Prefill 685.5 ·
  8. llama.cpp · Q5_K_M Decode 133.3 · Prefill 999.8 ·

Core figures

Decode (avg)
118.71 tok/s
Prefill (avg)
394.1 tok/s
TTFT (avg)
0.47 s
VRAM (avg)
17.22 GB
MTP acceptance rate
—
TTFB
0.95 GB
Power draw
337.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.32
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
17.22 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
12.4
Power draw
337.7 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.32 · Ubuntu 24.04 · CUDA 12.4 · 4096 ctx

    118.71 tok/s

    Decode

    394.1 tok/s

    Prefill

    0.47 s

    TTFT

    17.22 GB

    VRAM

    —

    MTP

    337.7 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=1 running model_id=69 at Q5_K_S