Back to search results
gemma-4-E4B-it · Q3_K_M
Apple M1 ProvLLM v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E4B-it (Q3_K_M) on Apple M1 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
98.62 tok/s
Decode
Decode speed
525.36 tok/s
Prefill
Prefill speed
0.99 s
TTFT
Time to first token
7.81 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q2_K Decode 122.43 · Prefill 598.25 ·
- vLLM · Q3_K_M (current)Decode 98.62 · Prefill 525.36 ·
- Ollama · Q4_K_S Decode 77.92 · Prefill 280.34 ·
Core figures
- Decode (avg)
- 98.62 tok/s
- Prefill (avg)
- 525.36 tok/s
- TTFT (avg)
- 0.99 s
- VRAM (avg)
- 7.81 GB
- MTP acceptance rate
- —
- TTFB
- 0.79 GB
- Power draw
- 47.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E4B-it
- Quantization
- Q3_K_M
- Framework
- vLLM
- Version
- v0.53
- 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
- Apple M1 Pro
- Measured VRAM (avg)
- 7.81 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 47.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · macOS 15.0 · CUDA N/A · 8192 ctx
98.62 tok/s
Decode
525.36 tok/s
Prefill
0.99 s
TTFT
7.81 GB
VRAM
—
MTP
47.7 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=100 running model_id=67 at Q3_K_M