← Back to community benchmarks
Qwen3.5-2B
Performance
4k
tokens
865.2
PP tok/s
36.9
TG tok/s
4734
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 854.3 | 37.9 | 3.2 GB | view |
| 4k | 865.2 | 36.9 | 3.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.9 | 1.00× |
| 2× | 78.5 | 2.07× |
| 4× | 129.0 | 3.40× |