← Back to community benchmarks

Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning

M2 Max (30c) · 32 GB · 8bit · 2026-04-28
Performance
4k
tokens
321.6
PP tok/s
35.8
TG tok/s
12738
TTFT (ms)
9.0
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 323.2 41.3 8.7 GB view
4k 321.6 35.8 9.0 GB current
Batching Results
Batch Size TG tok/s Speedup
41.3 1.00×
70.7 1.71×
141.2 3.42×