← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
1,151
PP tok/s
68.0
TG tok/s
3559
TTFT (ms)
2.3
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.18
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,060 | 81.6 | 1.9 GB | view |
| 4k | 1,151 | 68.0 | 2.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 81.6 | 1.00× |
| 2× | 70.9 | 0.87× |
| 4× | 116.0 | 1.42× |
| 8× | 155.2 | 1.90× |