← Back to community benchmarks

granite-4.0-h-tiny-oQ8e

M1 Ultra (48c) · 64 GB · 8bit · 2026-04-30
Performance
16k
tokens
1,460
PP tok/s
82.1
TG tok/s
11224
TTFT (ms)
10.3
Peak mem (GB)
Hardware
Chip M1 Ultra (48c)
Memory 64 GB
GPU Cores 48
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 954.3 96.2 9.1 GB view
4k 1,418 92.8 10.2 GB view
8k 1,480 90.1 10.2 GB view
16k 1,460 82.1 10.3 GB current
Batching Results
Batch Size TG tok/s Speedup
96.2 1.00×
166.1 1.73×
244.1 2.54×
327.0 3.40×