← Back to community benchmarks

gemma-4-26B-A4B-it-Claude-Opus-Distilled-v23bit-int3-affine

M4 (10c) · 24 GB · 3bit · 2026-05-19
Performance
16k
tokens
282.6
PP tok/s
27.4
TG tok/s
57968
TTFT (ms)
14.1
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 315.4 33.2 12.8 GB view
4k 315.9 32.3 13.4 GB view
8k 302.2 30.8 13.6 GB view
16k 282.6 27.4 14.1 GB current
32k 223.6 23.2 15.0 GB view