← Back to community benchmarks
Qwen3.5-0.8B
Performance
64k
tokens
1,861
PP tok/s
88.6
TG tok/s
35212
TTFT (ms)
4.1
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,837 | 303.8 | 1.7 GB | view |
| 4k | 3,714 | 276.7 | 1.9 GB | view |
| 8k | 3,503 | 248.1 | 1.9 GB | view |
| 16k | 3,125 | 202.9 | 2.1 GB | view |
| 32k | 2,563 | 143.9 | 2.8 GB | view |
| 64k | 1,861 | 88.6 | 4.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 303.8 | 1.00× |
| 2× | 478.7 | 1.58× |
| 4× | 583.2 | 1.92× |