Arao AI
Back to search results

Llama-3-8B-Instruct · IQ3_XS

Start a discussion
NVIDIA RTX 4080 Super16GBOllama v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (IQ3_XS) on NVIDIA RTX 4080 Super with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

184.92 tok/s

Decode

Decode speed

617.23 tok/s

Prefill

Prefill speed

1.92 s

TTFT

Time to first token

12.52 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q3_K_S Decode 189.4 · Prefill 632.63 ·
  2. Ollama · IQ1_S Decode 212.31 · Prefill 982.11 ·
  3. Ollama · IQ3_XS (current)Decode 184.92 · Prefill 617.23 ·

Core figures

Decode (avg)
184.92 tok/s
Prefill (avg)
617.23 tok/s
TTFT (avg)
1.92 s
VRAM (avg)
12.52 GB
MTP acceptance rate
—
TTFB
1.48 GB
Power draw
235 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
IQ3_XS
Framework
Ollama
Version
v0.34
Context length
4096 tokens
Batch size
256
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 4080 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
12.52 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.4
Power draw
235 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.34 · Ubuntu 24.04 · CUDA 12.4 · 4096 ctx

    184.92 tok/s

    Decode

    617.23 tok/s

    Prefill

    1.92 s

    TTFT

    12.52 GB

    VRAM

    —

    MTP

    235 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=20 running model_id=69 at IQ3_XS