← Back to community benchmarks

Llama-3.3-70B-Instruct-abliterated

M4 Max (40c) · 128 GB · 4bit · 2026-03-10
Performance
1k
tokens
94.4
PP tok/s
11.1
TG tok/s
10863
TTFT (ms)
37.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 94.4 11.1 37.8 GB current
4k 76.3 9.6 39.0 GB view
Batching Results
Batch Size TG tok/s Speedup
11.1 1.00×
13.5 1.22×
16.8 1.51×