← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
438.8
PP tok/s
67.9
TG tok/s
9334
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 429.2 | 73.6 | 4.0 GB | view |
| 4k | 438.8 | 67.9 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.6 | 1.00× |
| 2× | 85.7 | 1.16× |
| 4× | 92.3 | 1.25× |