NVIDIA-Nemotron-3.5-Bolt-E4B-4GB · BF16
This page aggregates 1 real-world runs of NVIDIA-Nemotron-3.5-Bolt-E4B-4GB (BF16) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
171.53 tok/s
Decode
Decode speed
804.96 tok/s
Prefill
Prefill speed
0.25 s
TTFT
Time to first token
30.4 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
12 days ago
Last verified
Performance
- vLLM · BF16 (current)Decode 171.53 · Prefill 804.96 ·
- Ollama · Q4_K_M Decode 279.75 · Prefill 1289.8 ·
Core figures
- Decode (avg)
- 171.53 tok/s
- Prefill (avg)
- 804.96 tok/s
- TTFT (avg)
- 0.25 s
- VRAM (avg)
- 30.4 GB
- MTP acceptance rate
- —
- TTFB
- 1.37 GB
- Power draw
- 435.1 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
- v0.50
- Context length
- 8192 tokens
- Batch size
- 32
- 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 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 30.4 GB
- OS
- Ubuntu 22.04
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 435.1 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
v0.50 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx
171.53 tok/s
Decode
804.96 tok/s
Prefill
0.25 s
TTFT
30.4 GB
VRAM
—
MTP
435.1 W
Power draw
L2 batch seed 2026-10-24: vLLM on hw_id=13 running model_id=97 at BF16