Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q8_0

Start a discussion
NVIDIA RTX 508016GBOllama v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q8_0) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

294.03 tok/s

Decode

Decode speed

1,167.26 tok/s

Prefill

Prefill speed

1.66 s

TTFT

Time to first token

9.35 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 Decode 381.8 · Prefill 1978.14 ·
  2. Ollama · Q5_K_S Decode 312.17 · Prefill 1673.45 ·
  3. Ollama · Q8_0 (current)Decode 294.03 · Prefill 1167.26 ·
  4. llama.cpp · IQ1_S Decode 351.28 · Prefill 1853.09 ·
  5. Ollama · IQ4_XS Decode 362.6 · Prefill 1325.05 ·

Core figures

Decode (avg)
294.03 tok/s
Prefill (avg)
1,167.26 tok/s
TTFT (avg)
1.66 s
VRAM (avg)
9.35 GB
MTP acceptance rate
—
TTFB
2.35 GB
Power draw
255.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q8_0
Framework
Ollama
Version
v0.30
Context length
16384 tokens
Batch size
512
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
9.35 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.6
Power draw
255.9 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

    v0.30 · Ubuntu 24.04 · CUDA 12.6 · 16384 ctx

    294.03 tok/s

    Decode

    1,167.26 tok/s

    Prefill

    1.66 s

    TTFT

    9.35 GB

    VRAM

    —

    MTP

    255.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=14 running model_id=70 at Q8_0