Arao AI
Back to search results

Llama-3-8B-Instruct · Q3_K_S

Start a discussion
NVIDIA RTX Spark128GBOllama v0.39L2 Cross-framework verified

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

56.77 tok/s

Decode

Decode speed

268.38 tok/s

Prefill

Prefill speed

2.38 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

16 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_M Decode 50.11 · Prefill 261.83 ·
  2. llama.cpp · Q5_K_S Decode 49.33 · Prefill 259.05 ·
  3. Ollama · Q3_K_S (current)Decode 56.77 · Prefill 268.38 ·
  4. Ollama · Q4_K_M Decode 51.27 · Prefill 167.27 ·

Core figures

Decode (avg)
56.77 tok/s
Prefill (avg)
268.38 tok/s
TTFT (avg)
2.38 s
VRAM (avg)
13.02 GB
MTP acceptance rate
—
TTFB
0.45 GB
Power draw
69.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q3_K_S
Framework
Ollama
Version
v0.39
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 Spark
Nominal VRAM
128 GB
Measured VRAM (avg)
13.02 GB
OS
Windows 11 24H2
Driver
NVIDIA 590.10
CUDA
13.0
Power draw
69.3 W
Reference price
$2,399 · updated 2026-10-19

Prices are not live; check the store page

Sources & evidence

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

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

    v0.39 · Windows 11 24H2 · CUDA 13.0 · 4096 ctx

    56.77 tok/s

    Decode

    268.38 tok/s

    Prefill

    2.38 s

    TTFT

    13.02 GB

    VRAM

    —

    MTP

    69.3 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=110 running model_id=69 at Q3_K_S