← Back to community benchmarks
Qwen3.5-0.8B-OptiQ
Performance
1k
tokens
1,432
PP tok/s
126.5
TG tok/s
715
TTFT (ms)
1.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,432 | 126.5 | 1.6 GB | current |
| 4k | 1,787 | 114.8 | 1.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 126.5 | 1.00× |
| 2× | 230.7 | 1.82× |
| 4× | 334.6 | 2.65× |