← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
124.2
PP tok/s
19.9
TG tok/s
32991
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M1 (7c)
Memory
16 GB
GPU Cores
7
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 124.7 | 20.5 | 3.9 GB | view |
| 4k | 124.2 | 19.9 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.5 | 1.00× |
| 2× | 28.2 | 1.38× |
| 4× | 28.9 | 1.41× |
| 8× | 24.5 | 1.20× |