Arao AI
Back to search results

Llama-3-8B-Instruct · Q2_K

Start a discussion
Intel Arc B58012GBvLLM v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q2_K) on Intel Arc B580 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

76.78 tok/s

Decode

Decode speed

352.63 tok/s

Prefill

Prefill speed

1.46 s

TTFT

Time to first token

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

Core figures

Decode (avg)
76.78 tok/s
Prefill (avg)
352.63 tok/s
TTFT (avg)
1.46 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
0.61 GB
Power draw
132.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q2_K
Framework
vLLM
Version
v0.42
Context length
16384 tokens
Batch size
16
GPU layers
999
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)
11.34 GB
OS
Windows 11 24H2
Driver
Intel Arc 32.0.101.6552
CUDA
12.6
Power draw
132.4 W

Sources & evidence

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

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

    v0.42 · Windows 11 24H2 · CUDA 12.6 · 16384 ctx

    76.78 tok/s

    Decode

    352.63 tok/s

    Prefill

    1.46 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    132.4 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=94 running model_id=69 at Q2_K