Back to search results
gemma-4-E2B-it · Q8_0
Apple M1 MaxvLLM v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (Q8_0) on Apple M1 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
98.82 tok/s
Decode
Decode speed
455.48 tok/s
Prefill
Prefill speed
0.82 s
TTFT
Time to first token
6.93 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q3_K_S Decode 189.55 · Prefill 943.94 ·
- vLLM · Q8_0 (current)Decode 98.82 · Prefill 455.48 ·
- Strata · IQ1_S Decode 324.26 · Prefill 1495.83 ·
Core figures
- Decode (avg)
- 98.82 tok/s
- Prefill (avg)
- 455.48 tok/s
- TTFT (avg)
- 0.82 s
- VRAM (avg)
- 6.93 GB
- MTP acceptance rate
- —
- TTFB
- 0.79 GB
- Power draw
- 20.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- Q8_0
- Framework
- vLLM
- Version
- v0.26
- Context length
- 32768 tokens
- Batch size
- 8
- 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 Max
- Measured VRAM (avg)
- 6.93 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Max
- CUDA
- N/A
- Power draw
- 20.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 15.0 · CUDA N/A · 32768 ctx
98.82 tok/s
Decode
455.48 tok/s
Prefill
0.82 s
TTFT
6.93 GB
VRAM
—
MTP
20.7 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=101 running model_id=66 at Q8_0