Back to search results
gemma-4-26B-A4B-it · Q6_K
Apple M5 Pro64GBStrata v0.52L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-26B-A4B-it (Q6_K) on Apple M5 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
98.9 tok/s
Decode
Decode speed
379.8 tok/s
Prefill
Prefill speed
1.66 s
TTFT
Time to first token
56.7 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 · Q8_0 Decode 55.26 · Prefill 261.28 ·
- Strata · Q6_K (current)Decode 98.9 · Prefill 379.8 ·
Core figures
- Decode (avg)
- 98.9 tok/s
- Prefill (avg)
- 379.8 tok/s
- TTFT (avg)
- 1.66 s
- VRAM (avg)
- 56.7 GB
- MTP acceptance rate
- 0.62
- TTFB
- 0.79 GB
- Power draw
- 76.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-26B-A4B-it
- Quantization
- Q6_K
- Framework
- Strata
- Version
- v0.52
- Context length
- 32768 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 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 56.7 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Pro
- CUDA
- N/A
- Power draw
- 76.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.52 · macOS 15.0 · CUDA N/A · 32768 ctx
98.9 tok/s
Decode
379.8 tok/s
Prefill
1.66 s
TTFT
56.7 GB
VRAM
0.62
MTP
76.4 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=27 running model_id=64 at Q6_K