← Back to community benchmarks

gemma-4-26B-A4B-it-uncensored-oQ5

M1 Max (32c) · 64 GB · 5bit · 2026-05-11
Performance
32k
tokens
678.2
PP tok/s
32.5
TG tok/s
48318
TTFT (ms)
19.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 15.7.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 678.2 32.5 19.1 GB current
64k 557.6 22.4 21.6 GB view