Arao AI
Back to search results

elephant-1 · FP16

Start a discussion
Apple M5 Max128GBOllama v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of elephant-1 (FP16) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

30.75 tok/s

Decode

Decode speed

124.45 tok/s

Prefill

Prefill speed

0.39 s

TTFT

Time to first token

37.06 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

14 days ago

Last verified

Performance

  1. llama.cpp · Q5_K_S Decode 59.51 · Prefill 259.7 ·
  2. Ollama · FP16 (current)Decode 30.75 · Prefill 124.45 ·
  3. Ollama · Q5_K_S Decode 53.6 · Prefill 253.24 ·

Core figures

Decode (avg)
30.75 tok/s
Prefill (avg)
124.45 tok/s
TTFT (avg)
0.39 s
VRAM (avg)
37.06 GB
MTP acceptance rate
—
TTFB
0.25 GB
Power draw
65.2 W

Configuration

Member-level fields are taken from the most recent run

Model
elephant-1
Quantization
FP16
Framework
Ollama
Version
v0.44
Context length
4096 tokens
Batch size
512
GPU layers
99
Flash Attention
On

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)
37.06 GB
OS
macOS 26.1
Power draw
65.2 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-22

    v0.44 · macOS 26.1 · 4096 ctx

    30.75 tok/s

    Decode

    124.45 tok/s

    Prefill

    0.39 s

    TTFT

    37.06 GB

    VRAM

    —

    MTP

    65.2 W

    Power draw

    L2 batch seed 2026-10-22: Ollama on hw_id=28 running model_id=95 at FP16