← Back to community benchmarks
Qwen3.5-0.8B-OptiQ
Performance
1k
tokens
1,577
PP tok/s
135.5
TG tok/s
649
TTFT (ms)
1.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,577 | 135.5 | 1.6 GB | current |
| 4k | 2,037 | 126.0 | 1.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 135.5 | 1.00× |
| 2× | 249.1 | 1.84× |
| 4× | 355.6 | 2.62× |