← Back to community benchmarks
Qwen3.5-4B-Heretic
Performance
4k
tokens
208.6
PP tok/s
30.5
TG tok/s
19634
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip
M2 (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 | 209.7 | 32.9 | 3.3 GB | view |
| 4k | 208.6 | 30.5 | 3.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.9 | 1.00× |
| 2× | 38.6 | 1.17× |
| 4× | 28.0 | 0.85× |