← Back to community benchmarks

gemma-4-26B-A4B-it-uncensored-abliterix4bit

M3 Max (30c) · 36 GB · 4bit · 2026-05-11
Performance
1k
tokens
797.9
PP tok/s
68.3
TG tok/s
1283
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 797.9 68.3 14.3 GB current
64k 588.8 38.3 17.7 GB view