← Back to community benchmarks

gemma-4-26b-a4b-mxfp8

M1 Ultra (48c) · 128 GB · 8bit · 2026-04-05
Performance
8k
tokens
704.0
PP tok/s
31.6
TG tok/s
11638
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip M1 Ultra (48c)
Memory 128 GB
GPU Cores 48
Software
oMLX v0.3.2
macOS macOS 15.7.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 676.0 36.8 26.1 GB view
4k 710.4 34.8 26.6 GB view
8k 704.0 31.6 26.7 GB current
Batching Results
Batch Size TG tok/s Speedup
36.8 1.00×
35.3 0.96×
36.4 0.99×