NVIDIA-Nemotron-3.5-Bolt-E4B-4GB · Q4_K_M
This page aggregates 1 real-world runs of NVIDIA-Nemotron-3.5-Bolt-E4B-4GB (Q4_K_M) on NVIDIA RTX 3090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
94.58 tok/s
Decode
Decode speed
353.95 tok/s
Prefill
Prefill speed
1 s
TTFT
Time to first token
15.88 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
12 days ago
Last verified
Performance
- llama.cpp · Q4_K_M (current)Decode 94.58 · Prefill 353.95 ·
- Strata · Q4_K_M Decode 125.83 · Prefill 630.14 ·
Core figures
- Decode (avg)
- 94.58 tok/s
- Prefill (avg)
- 353.95 tok/s
- TTFT (avg)
- 1 s
- VRAM (avg)
- 15.88 GB
- MTP acceptance rate
- 0.73
- TTFB
- 0.76 GB
- Power draw
- 286.1 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
- llama.cpp
- Version
- v0.30
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 15.88 GB
- OS
- Windows 11 23H2
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 286.1 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
v0.30 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx
94.58 tok/s
Decode
353.95 tok/s
Prefill
1 s
TTFT
15.88 GB
VRAM
0.73
MTP
286.1 W
Power draw
L2 batch seed 2026-10-24: llama.cpp on hw_id=2 running model_id=97 at Q4_K_M