Arao AI
Back to search results

mammoth-1 · IQ4_XS

Start a discussion
Apple M5 Max128GBllama.cpp v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of mammoth-1 (IQ4_XS) on Apple M5 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

59.77 tok/s

Decode

Decode speed

305.47 tok/s

Prefill

Prefill speed

0.51 s

TTFT

Time to first token

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

Core figures

Decode (avg)
59.77 tok/s
Prefill (avg)
305.47 tok/s
TTFT (avg)
0.51 s
VRAM (avg)
44.06 GB
MTP acceptance rate
—
TTFB
0.48 GB
Power draw
56.4 W

Configuration

Member-level fields are taken from the most recent run

Model
mammoth-1
Quantization
IQ4_XS
Framework
llama.cpp
Version
v0.25
Context length
32768 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)
44.06 GB
OS
macOS 26.1
Power draw
56.4 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

    v0.25 · macOS 26.1 · 32768 ctx

    59.77 tok/s

    Decode

    305.47 tok/s

    Prefill

    0.51 s

    TTFT

    44.06 GB

    VRAM

    —

    MTP

    56.4 W

    Power draw

    L2 batch seed 2026-10-22: llama.cpp on hw_id=28 running model_id=94 at IQ4_XS