← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
324.4
PP tok/s
103.9
TG tok/s
3157
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 324.4 | 103.9 | 4.0 GB | current |
| 4k | 310.4 | 34.9 | 3.9 GB | view |