← Back to community benchmarks
Qwen3.5-2B
Performance
4k
tokens
651.1
PP tok/s
50.1
TG tok/s
6291
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 742.0 | 41.8 | 2.9 GB | view |
| 4k | 651.1 | 50.1 | 3.0 GB | current |
| 8k | 724.8 | 46.2 | 3.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.8 | 1.00× |
| 2× | 64.4 | 1.54× |
| 4× | 60.5 | 1.45× |
| 8× | 64.6 | 1.55× |