← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
1,638
PP tok/s
13.1
TG tok/s
2501
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,416 | 13.5 | 3.3 GB | view |
| 4k | 1,638 | 13.1 | 3.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.5 | 1.00× |
| 2× | 25.9 | 1.92× |
| 4× | 50.4 | 3.73× |