Back to search results
gemma-4-12B-it · Q5_K_S
Apple M5 Ultra512GBOllama v0.46L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-12B-it (Q5_K_S) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
66.58 tok/s
Decode
Decode speed
239.33 tok/s
Prefill
Prefill speed
0.17 s
TTFT
Time to first token
24.78 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · IQ3_XS Decode 105.53 · Prefill 434.57 ·
- Ollama · Q3_K_L Decode 86.92 · Prefill 466.52 ·
- Ollama · Q5_K_S (current)Decode 66.58 · Prefill 239.33 ·
Core figures
- Decode (avg)
- 66.58 tok/s
- Prefill (avg)
- 239.33 tok/s
- TTFT (avg)
- 0.17 s
- VRAM (avg)
- 24.78 GB
- MTP acceptance rate
- —
- TTFB
- 0.53 GB
- Power draw
- 115.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- Q5_K_S
- Framework
- Ollama
- Version
- v0.46
- Context length
- 4096 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 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 24.78 GB
- OS
- macOS 26.1
- Power draw
- 115.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.46 · macOS 26.1 · 4096 ctx
66.58 tok/s
Decode
239.33 tok/s
Prefill
0.17 s
TTFT
24.78 GB
VRAM
—
MTP
115.7 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=65 at Q5_K_S