← Back to community benchmarks
Qwen3.5-2B
Performance
4k
tokens
1,038
PP tok/s
80.5
TG tok/s
3945
TTFT (ms)
2.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,043 | 83.9 | 2.5 GB | view |
| 4k | 1,038 | 80.5 | 2.5 GB | current |
| 8k | 1,020 | 76.0 | 2.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 83.9 | 1.00× |
| 2× | 157.9 | 1.88× |
| 4× | 204.5 | 2.44× |