Arao AI
Back to search results

Llama-3-8B-Instruct · IQ3_S

Start a discussion
Intel Arc B58012GBllama.cpp v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (IQ3_S) on Intel Arc B580 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

60.72 tok/s

Decode

Decode speed

260.85 tok/s

Prefill

Prefill speed

0.68 s

TTFT

Time to first token

11.4 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_S (current)Decode 60.72 · Prefill 260.85 ·
  2. vLLM · IQ1_S Decode 85.09 · Prefill 376.72 ·
  3. vLLM · Q2_K Decode 76.78 · Prefill 352.63 ·

Core figures

Decode (avg)
60.72 tok/s
Prefill (avg)
260.85 tok/s
TTFT (avg)
0.68 s
VRAM (avg)
11.4 GB
MTP acceptance rate
—
TTFB
0.49 GB
Power draw
135.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
IQ3_S
Framework
llama.cpp
Version
v0.46
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
On

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)
11.4 GB
OS
Windows 11 24H2
Driver
Intel Arc 32.0.101.6552
CUDA
12.4
Power draw
135.9 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

    v0.46 · Windows 11 24H2 · CUDA 12.4 · 4096 ctx

    60.72 tok/s

    Decode

    260.85 tok/s

    Prefill

    0.68 s

    TTFT

    11.4 GB

    VRAM

    —

    MTP

    135.9 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=94 running model_id=69 at IQ3_S