Arao AI
Back to search results

Llama-3.1-8B-Instruct · IQ2_XS

Start a discussion
NVIDIA RTX 309024GBOllama v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ2_XS) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

106.45 tok/s

Decode

Decode speed

486.76 tok/s

Prefill

Prefill speed

0.8 s

TTFT

Time to first token

10.16 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ3_XS Decode 111.47 · Prefill 506.1 ·
  2. llama.cpp · Q4_K_M Decode 116.04 · Prefill 765.01 ·
  3. Ollama · IQ2_XS (current)Decode 106.45 · Prefill 486.76 ·
  4. llama.cpp · Q8_0 Decode 84.9 · Prefill 636.8 ·
  5. llama.cpp · Q5_K_M Decode 123.7 · Prefill 927.8 ·

Core figures

Decode (avg)
106.45 tok/s
Prefill (avg)
486.76 tok/s
TTFT (avg)
0.8 s
VRAM (avg)
10.16 GB
MTP acceptance rate
—
TTFB
0.85 GB
Power draw
285.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
IQ2_XS
Framework
Ollama
Version
v0.34
Context length
4096 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 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
10.16 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
13.0
Power draw
285.9 W

Sources & evidence

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

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

    v0.34 · Ubuntu 24.04 · CUDA 13.0 · 4096 ctx

    106.45 tok/s

    Decode

    486.76 tok/s

    Prefill

    0.8 s

    TTFT

    10.16 GB

    VRAM

    —

    MTP

    285.9 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=2 running model_id=68 at IQ2_XS