Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q4_K_M

Start a discussion
NVIDIA RTX Spark128GBOllama v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q4_K_M) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

76.59 tok/s

Decode

Decode speed

359.8 tok/s

Prefill

Prefill speed

0.51 s

TTFT

Time to first token

7.27 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 · IQ3_S Decode 108.82 · Prefill 395.74 ·
  2. llama.cpp · Q4_K_M Decode 89.55 · Prefill 296 ·
  3. Ollama · IQ2_XS Decode 115.72 · Prefill 413.02 ·
  4. Ollama · Q4_K_M (current)Decode 76.59 · Prefill 359.8 ·

Core figures

Decode (avg)
76.59 tok/s
Prefill (avg)
359.8 tok/s
TTFT (avg)
0.51 s
VRAM (avg)
7.27 GB
MTP acceptance rate
—
TTFB
0.61 GB
Power draw
80.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q4_K_M
Framework
Ollama
Version
v0.52
Context length
32768 tokens
Batch size
512
GPU layers
99
Flash Attention
On

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)
7.27 GB
OS
Ubuntu 24.04
Driver
NVIDIA 590.10
CUDA
13.0
Power draw
80.3 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

    v0.52 · Ubuntu 24.04 · CUDA 13.0 · 32768 ctx

    76.59 tok/s

    Decode

    359.8 tok/s

    Prefill

    0.51 s

    TTFT

    7.27 GB

    VRAM

    —

    MTP

    80.3 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=110 running model_id=70 at Q4_K_M