← Back to community benchmarks
Qwen3.5-4B
Performance
8k
tokens
4,644
PP tok/s
141.9
TG tok/s
1764
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,819 | 165.3 | 3.4 GB | view |
| 4k | 4,336 | 153.0 | 4.2 GB | view |
| 8k | 4,644 | 141.9 | 4.6 GB | current |
| 16k | 4,535 | 123.3 | 5.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 165.3 | 1.00× |
| 2× | 292.2 | 1.77× |
| 4× | 412.6 | 2.50× |
| 8× | 473.8 | 2.87× |