← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
235.1
PP tok/s
17.0
TG tok/s
17422
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
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 | 236.8 | 18.0 | 3.9 GB | view |
| 4k | 235.1 | 17.0 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.0 | 1.00× |
| 2× | 33.5 | 1.86× |
| 4× | 52.8 | 2.93× |