← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-OS-HERETIC-UNCENSORED-INSTRUCT
Performance
1k
tokens
214.4
PP tok/s
20.8
TG tok/s
4777
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 214.4 | 20.8 | 5.7 GB | current |
| 4k | 221.9 | 20.3 | 6.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.8 | 1.00× |
| 2× | 40.2 | 1.93× |
| 4× | 52.0 | 2.50× |