Arao AI
Back to search results

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

Start a discussion
NVIDIA RTX 409024GBllama.cpp v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of NVIDIA-Nemotron-3.5-Bolt-E4B-4GB (Q4_K_M) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

160.59 tok/s

Decode

Decode speed

829.66 tok/s

Prefill

Prefill speed

2.32 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 160.59 · Prefill 829.66 ·
  2. Strata · Q4_K_M Decode 225.92 · Prefill 741.96 ·

Core figures

Decode (avg)
160.59 tok/s
Prefill (avg)
829.66 tok/s
TTFT (avg)
2.32 s
VRAM (avg)
15.88 GB
MTP acceptance rate
0.54
TTFB
1.28 GB
Power draw
324 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
v0.36
Context length
8192 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
15.88 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
324 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

    v0.36 · Ubuntu 22.04 · CUDA 12.6 · 8192 ctx

    160.59 tok/s

    Decode

    829.66 tok/s

    Prefill

    2.32 s

    TTFT

    15.88 GB

    VRAM

    0.54

    MTP

    324 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=1 running model_id=97 at Q4_K_M