← Back to community benchmarks
Qwen3.5-0.8B
Performance
8k
tokens
1,592
PP tok/s
12.2
TG tok/s
5147
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,269 | 12.6 | 3.3 GB | view |
| 4k | 1,610 | 12.5 | 3.4 GB | view |
| 8k | 1,592 | 12.2 | 3.6 GB | current |
| 16k | 1,429 | 11.6 | 4.4 GB | view |
| 32k | 1,109 | 10.8 | 5.8 GB | view |
| 64k | 712.7 | 9.3 | 6.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.6 | 1.00× |
| 2× | 23.0 | 1.83× |
| 4× | 45.0 | 3.57× |
| 8× | 88.5 | 7.02× |