Back to search results
gemma-4-12B-it · Q5_K_M
Apple M5 Max128GBOllama v0.49L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-12B-it (Q5_K_M) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
43.37 tok/s
Decode
Decode speed
143.55 tok/s
Prefill
Prefill speed
2.23 s
TTFT
Time to first token
25.54 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · IQ3_S Decode 67.49 · Prefill 263.38 ·
- Ollama · IQ2_M Decode 66.82 · Prefill 219.12 ·
- Ollama · Q5_K_M (current)Decode 43.37 · Prefill 143.55 ·
- Strata · Q4_K_S Decode 224.6 · Prefill 779.88 ·
Core figures
- Decode (avg)
- 43.37 tok/s
- Prefill (avg)
- 143.55 tok/s
- TTFT (avg)
- 2.23 s
- VRAM (avg)
- 25.54 GB
- MTP acceptance rate
- —
- TTFB
- 0.35 GB
- Power draw
- 54.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- Q5_K_M
- Framework
- Ollama
- Version
- v0.49
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 25.54 GB
- OS
- macOS 26.1
- Power draw
- 54.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.49 · macOS 26.1 · 32768 ctx
43.37 tok/s
Decode
143.55 tok/s
Prefill
2.23 s
TTFT
25.54 GB
VRAM
—
MTP
54.8 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=28 running model_id=65 at Q5_K_M