← Back to community benchmarks
Qwen3.5-2B
Performance
4k
tokens
1,019
PP tok/s
59.0
TG tok/s
4019
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,015 | 61.0 | 2.9 GB | view |
| 4k | 1,019 | 59.0 | 3.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.0 | 1.00× |
| 2× | 112.5 | 1.84× |
| 4× | 116.3 | 1.91× |