← Back to community benchmarks

gemma-3-1b-it

M1 Max (32c) · 64 GB · 4bit · 2026-05-15
Performance
195k
tokens
1,765
PP tok/s
57.7
TG tok/s
113289
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.0.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,264 178.9 1.2 GB view
4k 2,988 175.6 1.3 GB view
8k 3,389 168.7 1.4 GB view
16k 3,466 155.6 1.4 GB view
32k 3,308 133.8 1.4 GB view
64k 2,894 108.3 1.9 GB view
128k 2,152 76.3 2.7 GB view
195k 1,765 57.7 3.6 GB current
Batching Results
Batch Size TG tok/s Speedup
178.9 1.00×
284.3 1.59×
375.4 2.10×
528.0 2.95×