Arao AI
Back to search results

Llama-3-8B-Instruct · Q2_K

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

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

67.02 tok/s

Decode

Decode speed

263.91 tok/s

Prefill

Prefill speed

0.25 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

17 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_M Decode 57.84 · Prefill 315.13 ·
  2. Ollama · Q2_K (current)Decode 67.02 · Prefill 263.91 ·
  3. llama.cpp · IQ3_S Decode 60.72 · Prefill 260.85 ·
  4. vLLM · IQ1_S Decode 85.09 · Prefill 376.72 ·
  5. vLLM · Q2_K Decode 76.78 · Prefill 352.63 ·

Core figures

Decode (avg)
67.02 tok/s
Prefill (avg)
263.91 tok/s
TTFT (avg)
0.25 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
0.54 GB
Power draw
138 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q2_K
Framework
Ollama
Version
v0.48
Context length
16384 tokens
Batch size
512
GPU layers
33
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)
11.34 GB
OS
Ubuntu 24.04
Driver
Intel Arc 32.0.101.6552
CUDA
12.4
Power draw
138 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 · Ubuntu 24.04 · CUDA 12.4 · 16384 ctx

    67.02 tok/s

    Decode

    263.91 tok/s

    Prefill

    0.25 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    138 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=94 running model_id=69 at Q2_K