← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
66.4
PP tok/s
13.8
TG tok/s
15411
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 66.4 | 13.8 | 3.9 GB | current |
| 4k | 65.7 | 10.0 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.8 | 1.00× |
| 2× | 14.3 | 1.04× |
| 4× | 13.6 | 0.99× |
| 8× | 12.3 | 0.89× |