← Back to community benchmarks

supergemma4-26b-uncensored4bit-v2

M1 Max (32c) · 64 GB · 4bit · 2026-04-16
Performance
16k
tokens
480.2
PP tok/s
29.5
TG tok/s
34122
TTFT (ms)
14.9
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.5
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 439.8 57.9 14.0 GB view
4k 484.2 52.5 14.4 GB view
16k 480.2 29.5 14.9 GB current
Batching Results
Batch Size TG tok/s Speedup
57.9 1.00×
71.5 1.23×
88.0 1.52×