← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
259.5
PP tok/s
49.5
TG tok/s
3946
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
16 GB
GPU Cores
14
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 259.5 | 49.5 | 4.0 GB | current |
| 4k | 259.0 | 46.5 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.5 | 1.00× |
| 2× | 55.1 | 1.11× |
| 4× | 59.1 | 1.19× |