Arao AI
Back to search results

NVIDIA-Nemotron-3.5-Bolt-E4B-4GB · BF16

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBvLLM v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of NVIDIA-Nemotron-3.5-Bolt-E4B-4GB (BF16) on NVIDIA RTX PRO 6000 Blackwell 96GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

177.62 tok/s

Decode

Decode speed

884.45 tok/s

Prefill

Prefill speed

0.72 s

TTFT

Time to first token

31.5 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 (current)Decode 177.62 · Prefill 884.45 ·
  2. Ollama · Q4_K_M Decode 264.78 · Prefill 915.82 ·

Core figures

Decode (avg)
177.62 tok/s
Prefill (avg)
884.45 tok/s
TTFT (avg)
0.72 s
VRAM (avg)
31.5 GB
MTP acceptance rate
—
TTFB
1.42 GB
Power draw
350.6 W

Configuration

Member-level fields are taken from the most recent run

Model
NVIDIA-Nemotron-3.5-Bolt-E4B-4GB
Quantization
BF16
Framework
vLLM
Version
v0.36
Context length
16384 tokens
Batch size
16
GPU layers
999
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX PRO 6000 Blackwell 96GB
Nominal VRAM
96 GB
Measured VRAM (avg)
31.5 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.8
Power draw
350.6 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

    v0.36 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx

    177.62 tok/s

    Decode

    884.45 tok/s

    Prefill

    0.72 s

    TTFT

    31.5 GB

    VRAM

    —

    MTP

    350.6 W

    Power draw

    L2 batch seed 2026-10-24: vLLM on hw_id=68 running model_id=97 at BF16