Arao AI
Back to search results

NVIDIA-Nemotron-3.5-Bolt-E4B-4GB · Q4_K_M

Start a discussion
Apple M5 Ultra512GBllama.cpp v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of NVIDIA-Nemotron-3.5-Bolt-E4B-4GB (Q4_K_M) on Apple M5 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

130.96 tok/s

Decode

Decode speed

547.83 tok/s

Prefill

Prefill speed

1.48 s

TTFT

Time to first token

15.88 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_M (current)Decode 130.96 · Prefill 547.83 ·
  2. Ollama · Q4_K_M Decode 106.35 · Prefill 353.45 ·

Core figures

Decode (avg)
130.96 tok/s
Prefill (avg)
547.83 tok/s
TTFT (avg)
1.48 s
VRAM (avg)
15.88 GB
MTP acceptance rate
0.64
TTFB
1.05 GB
Power draw
135.6 W

Configuration

Member-level fields are taken from the most recent run

Model
NVIDIA-Nemotron-3.5-Bolt-E4B-4GB
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.45
Context length
4096 tokens
Batch size
256
GPU layers
28
Flash Attention
On

Hardware

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

GPU
Apple M5 Ultra
Nominal VRAM
512 GB
Measured VRAM (avg)
15.88 GB
OS
macOS 26.1
Power draw
135.6 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 2026-10-24

    v0.45 · macOS 26.1 · 4096 ctx

    130.96 tok/s

    Decode

    547.83 tok/s

    Prefill

    1.48 s

    TTFT

    15.88 GB

    VRAM

    0.64

    MTP

    135.6 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=29 running model_id=97 at Q4_K_M