← Back to community benchmarks

gpt-oss-120b-heretic-v2-mxfp4-q8-hi

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-15
Performance
1k
tokens
848.6
PP tok/s
66.0
TG tok/s
1207
TTFT (ms)
59.5
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 848.6 66.0 59.5 GB current
4k 1,294 68.4 59.6 GB view
8k 1,336 59.8 59.7 GB view
16k 1,283 49.9 60.1 GB view
32k 1,141 45.1 60.5 GB view
Batching Results
Batch Size TG tok/s Speedup
66.0 1.00×
87.6 1.33×
113.1 1.71×