← Back to community benchmarks

gm4-26b-a4b-ih

M5 Max (40c) · 64 GB · 4bit · 2026-05-01
Performance
32k
tokens
3,171
PP tok/s
83.5
TG tok/s
10335
TTFT (ms)
16.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,288 117.2 14.3 GB view
4k 3,367 112.1 14.8 GB view
32k 3,171 83.5 16.3 GB current
64k 2,250 61.7 18.5 GB view
Batching Results
Batch Size TG tok/s Speedup
117.2 1.00×
150.2 1.28×
207.2 1.77×