Back to search results
gemma-4-31B-it · Q3_K_M
Apple M5 Max128GBStrata v0.49L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-31B-it (Q3_K_M) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
149.39 tok/s
Decode
Decode speed
771.31 tok/s
Prefill
Prefill speed
1.71 s
TTFT
Time to first token
46.37 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Strata · IQ4_XS Decode 138.4 · Prefill 718.68 ·
- Strata · Q3_K_M (current)Decode 149.39 · Prefill 771.31 ·
Core figures
- Decode (avg)
- 149.39 tok/s
- Prefill (avg)
- 771.31 tok/s
- TTFT (avg)
- 1.71 s
- VRAM (avg)
- 46.37 GB
- MTP acceptance rate
- 0.47
- TTFB
- 1.2 GB
- Power draw
- 49.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-31B-it
- Quantization
- Q3_K_M
- Framework
- Strata
- Version
- v0.49
- Context length
- 8192 tokens
- Batch size
- 1024
- GPU layers
- 8
- 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)
- 46.37 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Max
- CUDA
- N/A
- Power draw
- 49.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.49 · macOS 15.0 · CUDA N/A · 8192 ctx
149.39 tok/s
Decode
771.31 tok/s
Prefill
1.71 s
TTFT
46.37 GB
VRAM
0.47
MTP
49.3 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=28 running model_id=63 at Q3_K_M