Arao AI
Back to search results

Llama-3.1-8B-Instruct · IQ2_XS

Start a discussion
Intel Arc B58012GBOllama v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ2_XS) on Intel Arc B580 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

70.97 tok/s

Decode

Decode speed

264.22 tok/s

Prefill

Prefill speed

2.13 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

16 days ago

Last verified

Performance

  1. llama.cpp · IQ3_S Decode 58.55 · Prefill 274.06 ·
  2. llama.cpp · Q3_K_S Decode 65.46 · Prefill 319.04 ·
  3. Ollama · IQ2_XS (current)Decode 70.97 · Prefill 264.22 ·
  4. Ollama · IQ2_M Decode 67.87 · Prefill 259.33 ·

Core figures

Decode (avg)
70.97 tok/s
Prefill (avg)
264.22 tok/s
TTFT (avg)
2.13 s
VRAM (avg)
10.16 GB
MTP acceptance rate
—
TTFB
0.57 GB
Power draw
137.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
IQ2_XS
Framework
Ollama
Version
v0.48
Context length
16384 tokens
Batch size
512
GPU layers
20
Flash Attention
Off

Hardware

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

GPU
Intel Arc B580
Nominal VRAM
12 GB
Measured VRAM (avg)
10.16 GB
OS
Windows 11 24H2
Driver
Intel Arc 32.0.101.6552
CUDA
12.6
Power draw
137.4 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

    v0.48 · Windows 11 24H2 · CUDA 12.6 · 16384 ctx

    70.97 tok/s

    Decode

    264.22 tok/s

    Prefill

    2.13 s

    TTFT

    10.16 GB

    VRAM

    —

    MTP

    137.4 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=94 running model_id=68 at IQ2_XS