← Back to community benchmarks
Qwen3.5-2B
Performance
1k
tokens
1,005
PP tok/s
61.1
TG tok/s
1019
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,005 | 61.1 | 2.9 GB | current |
| 4k | 1,012 | 58.5 | 3.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.1 | 1.00× |
| 2× | 64.8 | 1.06× |
| 4× | 119.9 | 1.96× |