Arao AI
Back to search results

Llama-3-8B-Instruct · IQ3_S

Start a discussion
NVIDIA RTX 508016GBOllama v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (IQ3_S) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

199.24 tok/s

Decode

Decode speed

946.23 tok/s

Prefill

Prefill speed

0.15 s

TTFT

Time to first token

13.19 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 · IQ3_S (current)Decode 199.24 · Prefill 946.23 ·
  2. Ollama · Q3_K_S Decode 204.49 · Prefill 898.01 ·
  3. Strata · IQ1_S Decode 349.68 · Prefill 1703.4 ·
  4. Strata · Q3_K_L Decode 297.89 · Prefill 1445.32 ·
  5. vLLM · Q5_K_M Decode 163.66 · Prefill 702.95 ·

Core figures

Decode (avg)
199.24 tok/s
Prefill (avg)
946.23 tok/s
TTFT (avg)
0.15 s
VRAM (avg)
13.19 GB
MTP acceptance rate
—
TTFB
1.59 GB
Power draw
287.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
IQ3_S
Framework
Ollama
Version
v0.39
Context length
32768 tokens
Batch size
256
GPU layers
28
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)
13.19 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.4
Power draw
287.1 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

    v0.39 · Ubuntu 24.04 · CUDA 12.4 · 32768 ctx

    199.24 tok/s

    Decode

    946.23 tok/s

    Prefill

    0.15 s

    TTFT

    13.19 GB

    VRAM

    —

    MTP

    287.1 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=14 running model_id=69 at IQ3_S