Arao AI
Back to search results

Llama-3-8B-Instruct · Q5_K_S

Start a discussion
NVIDIA RTX 309024GBOllama v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q5_K_S) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

67.97 tok/s

Decode

Decode speed

263.38 tok/s

Prefill

Prefill speed

0.42 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. Ollama · Q5_K_S (current)Decode 67.97 · Prefill 263.38 ·
  2. Strata · IQ3_S Decode 155.86 · Prefill 503.14 ·
  3. Strata · Q5_K_M Decode 101.92 · Prefill 340.28 ·
  4. Ollama · IQ3_S Decode 90.89 · Prefill 298.18 ·
  5. Ollama · Q4_K_M Decode 84.07 · Prefill 419.77 ·
  6. Strata · IQ4_XS Decode 126.45 · Prefill 522.82 ·
  7. Strata · Q3_K_M Decode 136.06 · Prefill 696.33 ·
  8. llama.cpp · Q8_0 Decode 84.9 · Prefill 636.8 ·
  9. llama.cpp · Q5_K_M Decode 123.7 · Prefill 927.8 ·
  10. llama.cpp · Q4_K_M Decode 149 · Prefill 1117.5 ·

Core figures

Decode (avg)
67.97 tok/s
Prefill (avg)
263.38 tok/s
TTFT (avg)
0.42 s
VRAM (avg)
17.22 GB
MTP acceptance rate
—
TTFB
0.54 GB
Power draw
320.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q5_K_S
Framework
Ollama
Version
v0.51
Context length
16384 tokens
Batch size
512
GPU layers
20
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
17.22 GB
OS
Windows 11 23H2
Driver
572.83
CUDA
12.8
Power draw
320.4 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

    v0.51 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx

    67.97 tok/s

    Decode

    263.38 tok/s

    Prefill

    0.42 s

    TTFT

    17.22 GB

    VRAM

    —

    MTP

    320.4 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=2 running model_id=69 at Q5_K_S