← Back to community benchmarks

gemma-4-26B-A4B-it-unsloth

M5 Max (40c) · 128 GB · bf16 · 2026-05-23
Performance
64k
tokens
2,411
PP tok/s
42.1
TG tok/s
27178
TTFT (ms)
51.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,083 59.1 47.8 GB view
4k 3,169 57.5 48.5 GB view
64k 2,411 42.1 51.2 GB current
Batching Results
Batch Size TG tok/s Speedup
59.1 1.00×
59.7 1.01×
102.4 1.73×