← Back to community benchmarks
Qwen3.5-2B
Performance
4k
tokens
1,046
PP tok/s
81.0
TG tok/s
3917
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 | 1,044 | 85.1 | 2.5 GB | view |
| 4k | 1,046 | 81.0 | 2.5 GB | current |
| 8k | 1,020 | 75.9 | 2.6 GB | view |
| 16k | 962.0 | 67.9 | 3.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.1 | 1.00× |
| 2× | 160.4 | 1.88× |
| 4× | 203.8 | 2.39× |