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 Apple M2 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
119.47 tok/s
Decode
Decode speed
397.94 tok/s
Prefill
Prefill speed
2.12 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 119.47 · Prefill 397.94 ·
- Ollama · Q4_K_M Decode 118.08 · Prefill 636.62 ·
Core figures
- Decode (avg)
- 119.47 tok/s
- Prefill (avg)
- 397.94 tok/s
- TTFT (avg)
- 2.12 s
- VRAM (avg)
- 15.88 GB
- MTP acceptance rate
- 0.66
- TTFB
- 0.96 GB
- Power draw
- 135.9 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
- 8192 tokens
- Batch size
- 512
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Ultra
- Measured VRAM (avg)
- 15.88 GB
- OS
- macOS 26.1
- Power draw
- 135.9 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 · macOS 26.1 · 8192 ctx
119.47 tok/s
Decode
397.94 tok/s
Prefill
2.12 s
TTFT
15.88 GB
VRAM
0.66
MTP
135.9 W
Power draw
L2 batch seed 2026-10-24: llama.cpp on hw_id=103 running model_id=97 at Q4_K_M