← Back to community benchmarks
Qwen3.5-0.8B
Performance
64k
tokens
766.3
PP tok/s
8.0
TG tok/s
85523
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 15.7.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,467 | 13.5 | 3.3 GB | view |
| 4k | 1,700 | 13.2 | 3.4 GB | view |
| 64k | 766.3 | 8.0 | 6.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.5 | 1.00× |
| 2× | 25.7 | 1.90× |
| 4× | 49.8 | 3.69× |