← Back to community benchmarks
Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning
Performance
1k
tokens
78.4
PP tok/s
7.2
TG tok/s
13081
TTFT (ms)
8.5
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 78.4 | 7.2 | 8.5 GB | current |
| 4k | 77.3 | 6.8 | 9.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.2 | 1.00× |
| 2× | 12.9 | 1.79× |
| 4× | 21.7 | 3.01× |