← Back to community benchmarks
Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning
Performance
1k
tokens
323.2
PP tok/s
41.3
TG tok/s
3171
TTFT (ms)
8.7
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 323.2 | 41.3 | 8.7 GB | current |
| 4k | 321.6 | 35.8 | 9.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.3 | 1.00× |
| 2× | 70.7 | 1.71× |
| 4× | 141.2 | 3.42× |