Back to search results
gemma-4-E2B-it · IQ3_S
Apple M1Ollama v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (IQ3_S) on Apple M1 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
89.33 tok/s
Decode
Decode speed
357.04 tok/s
Prefill
Prefill speed
0.37 s
TTFT
Time to first token
4.87 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ2_XS Decode 125.44 · Prefill 495.34 ·
- llama.cpp · Q6_K Decode 62.45 · Prefill 267.16 ·
- Ollama · IQ2_XS Decode 113.15 · Prefill 569.16 ·
- Ollama · IQ3_S (current)Decode 89.33 · Prefill 357.04 ·
Core figures
- Decode (avg)
- 89.33 tok/s
- Prefill (avg)
- 357.04 tok/s
- TTFT (avg)
- 0.37 s
- VRAM (avg)
- 4.87 GB
- MTP acceptance rate
- —
- TTFB
- 0.71 GB
- Power draw
- 29 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- IQ3_S
- Framework
- Ollama
- Version
- v0.44
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M1
- Measured VRAM (avg)
- 4.87 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 29 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · macOS 15.0 · CUDA N/A · 32768 ctx
89.33 tok/s
Decode
357.04 tok/s
Prefill
0.37 s
TTFT
4.87 GB
VRAM
—
MTP
29 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=99 running model_id=66 at IQ3_S