Arao AI
Back to search results

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

Start a discussion
NVIDIA RTX 409024GBStrata v0.44L2 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 Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

225.92 tok/s

Decode

Decode speed

741.96 tok/s

Prefill

Prefill speed

1.96 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 Decode 160.59 · Prefill 829.66 ·
  2. Strata · Q4_K_M (current)Decode 225.92 · Prefill 741.96 ·

Core figures

Decode (avg)
225.92 tok/s
Prefill (avg)
741.96 tok/s
TTFT (avg)
1.96 s
VRAM (avg)
15.88 GB
MTP acceptance rate
0.49
TTFB
1.81 GB
Power draw
304.8 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
Strata
Version
v0.44
Context length
8192 tokens
Batch size
512
GPU layers
5
Flash Attention
On

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
Windows 11 24H2
Driver
565.57
CUDA
12.6
Power draw
304.8 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 2026-10-24

    v0.44 · Windows 11 24H2 · CUDA 12.6 · 8192 ctx

    225.92 tok/s

    Decode

    741.96 tok/s

    Prefill

    1.96 s

    TTFT

    15.88 GB

    VRAM

    0.49

    MTP

    304.8 W

    Power draw

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