← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
305.4
PP tok/s
34.3
TG tok/s
13411
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M4 (8c)
Memory
16 GB
GPU Cores
8
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 | 308.3 | 37.1 | 3.9 GB | view |
| 4k | 305.4 | 34.3 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.1 | 1.00× |
| 2× | 67.3 | 1.81× |
| 4× | 70.8 | 1.91× |
| 8× | 69.3 | 1.87× |