Arao AI
Back to search results

Llama-3-8B-Instruct · IQ2_M

Start a discussion
Apple M5 Max128GBOllama v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (IQ2_M) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

100.02 tok/s

Decode

Decode speed

413.11 tok/s

Prefill

Prefill speed

0.18 s

TTFT

Time to first token

10.84 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 83.59 · Prefill 361.92 ·
  2. Ollama · IQ2_M (current)Decode 100.02 · Prefill 413.11 ·

Core figures

Decode (avg)
100.02 tok/s
Prefill (avg)
413.11 tok/s
TTFT (avg)
0.18 s
VRAM (avg)
10.84 GB
MTP acceptance rate
—
TTFB
0.8 GB
Power draw
68.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
IQ2_M
Framework
Ollama
Version
v0.35
Context length
32768 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

Hardware

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

GPU
Apple M5 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
10.84 GB
OS
macOS 26.1
Power draw
68.9 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.35 · macOS 26.1 · 32768 ctx

    100.02 tok/s

    Decode

    413.11 tok/s

    Prefill

    0.18 s

    TTFT

    10.84 GB

    VRAM

    —

    MTP

    68.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=28 running model_id=69 at IQ2_M