Arao AI
Back to search results

mammoth-1 · FP16

Start a discussion
Apple M5 Max128GBOllama v0.33L2 Cross-framework verified

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

25.66 tok/s

Decode

Decode speed

97.32 tok/s

Prefill

Prefill speed

0.16 s

TTFT

Time to first token

107 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

13 days ago

Last verified

Performance

  1. llama.cpp · IQ4_XS Decode 59.77 · Prefill 305.47 ·
  2. llama.cpp · Q3_K_M Decode 63.7 · Prefill 294.17 ·
  3. Ollama · FP16 (current)Decode 25.66 · Prefill 97.32 ·

Core figures

Decode (avg)
25.66 tok/s
Prefill (avg)
97.32 tok/s
TTFT (avg)
0.16 s
VRAM (avg)
107 GB
MTP acceptance rate
—
TTFB
0.21 GB
Power draw
59.8 W

Configuration

Member-level fields are taken from the most recent run

Model
mammoth-1
Quantization
FP16
Framework
Ollama
Version
v0.33
Context length
16384 tokens
Batch size
256
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
Apple M5 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
107 GB
OS
macOS 26.1
Power draw
59.8 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

    v0.33 · macOS 26.1 · 16384 ctx

    25.66 tok/s

    Decode

    97.32 tok/s

    Prefill

    0.16 s

    TTFT

    107 GB

    VRAM

    —

    MTP

    59.8 W

    Power draw

    L2 batch seed 2026-10-22: Ollama on hw_id=28 running model_id=94 at FP16