← Back to community benchmarks
Qwen3.5-4B
Performance
16k
tokens
879.7
PP tok/s
68.1
TG tok/s
18624
TTFT (ms)
5.2
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
96 GB
GPU Cores
30
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 874.5 | 91.4 | 3.4 GB | view |
| 4k | 994.9 | 86.2 | 4.1 GB | view |
| 8k | 988.3 | 79.2 | 4.5 GB | view |
| 16k | 879.7 | 68.1 | 5.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 91.4 | 1.00× |
| 2× | 156.8 | 1.72× |
| 4× | 206.7 | 2.26× |