Arao AI
Back to search results

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

Start a discussion
NVIDIA H100 80GB HBM380GBStrata v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of NVIDIA-Nemotron-3.5-Bolt-E4B-4GB (Q4_K_M) on NVIDIA H100 80GB HBM3 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

317.23 tok/s

Decode

Decode speed

1,729.64 tok/s

Prefill

Prefill speed

1.22 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. Ollama · Q4_K_M Decode 345.26 · Prefill 1726.58 ·
  2. Strata · Q4_K_M (current)Decode 317.23 · Prefill 1729.64 ·

Core figures

Decode (avg)
317.23 tok/s
Prefill (avg)
1,729.64 tok/s
TTFT (avg)
1.22 s
VRAM (avg)
15.88 GB
MTP acceptance rate
0.51
TTFB
2.54 GB
Power draw
649.6 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
Strata
Version
v0.41
Context length
32768 tokens
Batch size
512
GPU layers
8
Flash Attention
On

Hardware

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

GPU
NVIDIA H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
15.88 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.8
Power draw
649.6 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

    v0.41 · Ubuntu 22.04 · CUDA 12.8 · 32768 ctx

    317.23 tok/s

    Decode

    1,729.64 tok/s

    Prefill

    1.22 s

    TTFT

    15.88 GB

    VRAM

    0.51

    MTP

    649.6 W

    Power draw

    L2 batch seed 2026-10-24: Strata on hw_id=55 running model_id=97 at Q4_K_M