Back to search results
gemma-4-E2B-it · IQ2_XS
Apple M2 ProOllama v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (IQ2_XS) on Apple M2 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
158.03 tok/s
Decode
Decode speed
828.05 tok/s
Prefill
Prefill speed
2.36 s
TTFT
Time to first token
4.12 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q4_K_M Decode 128.43 · Prefill 487.16 ·
- Ollama · IQ2_XS (current)Decode 158.03 · Prefill 828.05 ·
- Ollama · Q3_K_S Decode 140.03 · Prefill 568.6 ·
Core figures
- Decode (avg)
- 158.03 tok/s
- Prefill (avg)
- 828.05 tok/s
- TTFT (avg)
- 2.36 s
- VRAM (avg)
- 4.12 GB
- MTP acceptance rate
- —
- TTFB
- 1.26 GB
- Power draw
- 55.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- IQ2_XS
- Framework
- Ollama
- Version
- v0.21
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Pro
- Measured VRAM (avg)
- 4.12 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 55.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · macOS 15.0 · CUDA N/A · 32768 ctx
158.03 tok/s
Decode
828.05 tok/s
Prefill
2.36 s
TTFT
4.12 GB
VRAM
—
MTP
55.9 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=102 running model_id=66 at IQ2_XS