Back to search results
gemma-4-26B-A4B-it · Q2_K
Apple M5 Max128GBStrata v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-26B-A4B-it (Q2_K) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
228.98 tok/s
Decode
Decode speed
895.33 tok/s
Prefill
Prefill speed
1.32 s
TTFT
Time to first token
32.13 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · Q3_K_S Decode 174.38 · Prefill 573.36 ·
- vLLM · Q4_K_S Decode 136.41 · Prefill 547.6 ·
- Strata · Q2_K (current)Decode 228.98 · Prefill 895.33 ·
- Strata · Q8_0 Decode 122.58 · Prefill 429.76 ·
Core figures
- Decode (avg)
- 228.98 tok/s
- Prefill (avg)
- 895.33 tok/s
- TTFT (avg)
- 1.32 s
- VRAM (avg)
- 32.13 GB
- MTP acceptance rate
- 0.49
- TTFB
- 1.83 GB
- Power draw
- 100.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-26B-A4B-it
- Quantization
- Q2_K
- Framework
- Strata
- Version
- v0.35
- Context length
- 2048 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)
- 32.13 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Max
- CUDA
- N/A
- Power draw
- 100.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · macOS 15.0 · CUDA N/A · 2048 ctx
228.98 tok/s
Decode
895.33 tok/s
Prefill
1.32 s
TTFT
32.13 GB
VRAM
0.49
MTP
100.4 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=28 running model_id=64 at Q2_K