← Back to community benchmarks
Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING
Performance
4k
tokens
384.0
PP tok/s
32.8
TG tok/s
10667
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 367.1 | 34.6 | 3.3 GB | view |
| 4k | 384.0 | 32.8 | 3.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.6 | 1.00× |
| 2× | 65.1 | 1.88× |
| 4× | 85.6 | 2.47× |