← Back to community benchmarks

Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4-oQ8e

M5 Max (40c) · 128 GB · 8bit · 2026-07-18
Performance
128k
tokens
1,546
PP tok/s
59.7
TG tok/s
84774
TTFT (ms)
47.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.2.dev1
macOS macOS 27.0
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,517 100.7 35.5 GB view
4k 4,307 97.7 36.3 GB view
32k 3,366 86.4 38.7 GB view
64k 2,437 75.6 41.9 GB view
128k 1,546 59.7 47.9 GB current
Batching Results
Batch Size TG tok/s Speedup
100.7 1.00×
159.8 1.59×
242.5 2.41×