Back to search results
gemma-4-12B-it · IQ2_M
Apple M4 Pro64GBllama.cpp v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_M) on Apple M4 Pro with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
103.7 tok/s
Decode
Decode speed
452.45 tok/s
Prefill
Prefill speed
1.42 s
TTFT
Time to first token
15.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ2_M (current)Decode 103.7 · Prefill 452.45 ·
- llama.cpp · Q5_K_S Decode 68.46 · Prefill 358.45 ·
- vLLM · Q2_K Decode 110.03 · Prefill 407.67 ·
- vLLM · Q4_K_S Decode 90.85 · Prefill 484.54 ·
Core figures
- Decode (avg)
- 103.7 tok/s
- Prefill (avg)
- 452.45 tok/s
- TTFT (avg)
- 1.42 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.83 GB
- Power draw
- 120 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- IQ2_M
- Framework
- llama.cpp
- Version
- v0.43
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M4 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 15.2 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 120 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · macOS 15.0 · CUDA N/A · 2048 ctx
103.7 tok/s
Decode
452.45 tok/s
Prefill
1.42 s
TTFT
15.2 GB
VRAM
—
MTP
120 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=25 running model_id=65 at IQ2_M