← Back to community benchmarks
Qwen3.5-0.8B
Performance
16k
tokens
745.7
PP tok/s
47.7
TG tok/s
21973
TTFT (ms)
2.4
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
8 GB
GPU Cores
8
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 850.9 | 61.8 | 1.8 GB | view |
| 4k | 847.6 | 59.1 | 1.9 GB | view |
| 8k | 814.5 | 54.1 | 2.0 GB | view |
| 16k | 745.7 | 47.7 | 2.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.8 | 1.00× |
| 2× | 118.9 | 1.92× |
| 4× | 169.9 | 2.75× |