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