Arao AI
Back to search results

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

Start a discussion
AMD Ryzen AI Max+ 395128GBllama.cpp v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of NVIDIA-Nemotron-3.5-Bolt-E4B-4GB (Q4_K_M) on AMD Ryzen AI Max+ 395 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

35.76 tok/s

Decode

Decode speed

167.23 tok/s

Prefill

Prefill speed

0.59 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 35.76 · Prefill 167.23 ·
  2. Ollama · Q4_K_M Decode 33.77 · Prefill 108.98 ·

Core figures

Decode (avg)
35.76 tok/s
Prefill (avg)
167.23 tok/s
TTFT (avg)
0.59 s
VRAM (avg)
15.88 GB
MTP acceptance rate
0.69
TTFB
0.29 GB
Power draw
45.3 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
v0.31
Context length
4096 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
AMD Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
15.88 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
12.6
Power draw
45.3 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

    v0.31 · Windows 11 23H2 · CUDA 12.6 · 4096 ctx

    35.76 tok/s

    Decode

    167.23 tok/s

    Prefill

    0.59 s

    TTFT

    15.88 GB

    VRAM

    0.69

    MTP

    45.3 W

    Power draw

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