← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
577.3
PP tok/s
88.8
TG tok/s
1774
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 577.3 | 88.8 | 4.0 GB | current |
| 4k | 578.1 | 82.8 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 88.8 | 1.00× |
| 2× | 108.6 | 1.22× |
| 4× | 122.7 | 1.38× |