Back to search results
gemma-4-12B-it · Q3_K_M
Apple M5 Pro64GBOllama v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-12B-it (Q3_K_M) on Apple M5 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
110.36 tok/s
Decode
Decode speed
569.49 tok/s
Prefill
Prefill speed
2.29 s
TTFT
Time to first token
19.24 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 · Q4_K_M Decode 100.37 · Prefill 374.04 ·
- llama.cpp · Q8_0 Decode 66.87 · Prefill 301.78 ·
- Ollama · Q3_K_M (current)Decode 110.36 · Prefill 569.49 ·
- Ollama · Q3_K_S Decode 111.33 · Prefill 497.48 ·
Core figures
- Decode (avg)
- 110.36 tok/s
- Prefill (avg)
- 569.49 tok/s
- TTFT (avg)
- 2.29 s
- VRAM (avg)
- 19.24 GB
- MTP acceptance rate
- —
- TTFB
- 0.88 GB
- Power draw
- 59.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.37
- 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 M5 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 19.24 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Pro
- CUDA
- N/A
- Power draw
- 59.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · macOS 15.0 · CUDA N/A · 32768 ctx
110.36 tok/s
Decode
569.49 tok/s
Prefill
2.29 s
TTFT
19.24 GB
VRAM
—
MTP
59.7 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=27 running model_id=65 at Q3_K_M