Arao AI
Back to search results

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

Start a discussion
NVIDIA RTX 509032GBOllama v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of NVIDIA-Nemotron-3.5-Bolt-E4B-4GB (Q4_K_M) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

279.75 tok/s

Decode

Decode speed

1,289.8 tok/s

Prefill

Prefill speed

1.24 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. vLLM · BF16 Decode 171.53 · Prefill 804.96 ·
  2. Ollama · Q4_K_M (current)Decode 279.75 · Prefill 1289.8 ·

Core figures

Decode (avg)
279.75 tok/s
Prefill (avg)
1,289.8 tok/s
TTFT (avg)
1.24 s
VRAM (avg)
15.88 GB
MTP acceptance rate
—
TTFB
2.24 GB
Power draw
466.6 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
Ollama
Version
v0.32
Context length
16384 tokens
Batch size
256
GPU layers
99
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
15.88 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.6
Power draw
466.6 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

    v0.32 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx

    279.75 tok/s

    Decode

    1,289.8 tok/s

    Prefill

    1.24 s

    TTFT

    15.88 GB

    VRAM

    —

    MTP

    466.6 W

    Power draw

    L2 batch seed 2026-10-24: Ollama on hw_id=13 running model_id=97 at Q4_K_M