← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Max (30c) · 32 GB · 4bit · 2026-04-20
Performance
32k
tokens
464.6
PP tok/s
15.2
TG tok/s
70532
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 466.2 64.8 14.2 GB view
4k 505.6 59.1 14.7 GB view
8k 508.3 45.6 14.8 GB view
16k 496.0 32.2 15.2 GB view
32k 464.6 15.2 16.0 GB current
64k 398.2 6.1 17.7 GB view
Batching Results
Batch Size TG tok/s Speedup
64.8 1.00×
81.4 1.26×
95.2 1.47×
107.2 1.65×