Back to search results
gemma-4-E2B-it · IQ2_XS
Apple M1llama.cpp v0.28L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (IQ2_XS) on Apple M1 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
125.44 tok/s
Decode
Decode speed
495.34 tok/s
Prefill
Prefill speed
1.32 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
- llama.cpp · IQ2_XS (current)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 Decode 89.33 · Prefill 357.04 ·
Core figures
- Decode (avg)
- 125.44 tok/s
- Prefill (avg)
- 495.34 tok/s
- TTFT (avg)
- 1.32 s
- VRAM (avg)
- 4.12 GB
- MTP acceptance rate
- —
- TTFB
- 1 GB
- Power draw
- 16.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- IQ2_XS
- Framework
- llama.cpp
- Version
- v0.28
- Context length
- 4096 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M1
- Measured VRAM (avg)
- 4.12 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 16.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.28 · macOS 15.0 · CUDA N/A · 4096 ctx
125.44 tok/s
Decode
495.34 tok/s
Prefill
1.32 s
TTFT
4.12 GB
VRAM
—
MTP
16.9 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=99 running model_id=66 at IQ2_XS