← Back to community benchmarks

gemma-4-26b-a4b

M3 Max (40c) · 64 GB · 4bit · 2026-04-12
Performance
4k
tokens
1,155
PP tok/s
78.3
TG tok/s
3548
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 875.9 84.6 14.2 GB view
4k 1,155 78.3 14.8 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 84.6 1.00×
2× 125.0 1.48×
4× 143.7 1.70×