← Back to community benchmarks
Qwen3.5-9B-Heretic
Performance
4k
tokens
203.0
PP tok/s
20.8
TG tok/s
20179
TTFT (ms)
6.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 206.3 | 17.4 | 5.8 GB | view |
| 4k | 203.0 | 20.8 | 6.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.4 | 1.00× |
| 2× | 31.0 | 1.78× |
| 4× | 45.1 | 2.59× |