← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
258.1
PP tok/s
49.3
TG tok/s
3968
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
16 GB
GPU Cores
14
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 258.1 | 49.3 | 4.0 GB | current |
| 4k | 256.7 | 45.9 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.3 | 1.00× |
| 2× | 55.3 | 1.12× |
| 4× | 58.9 | 1.19× |