← Back to community benchmarks
Qwen3.5-4B
Performance
64k
tokens
368.9
PP tok/s
21.9
TG tok/s
177630
TTFT (ms)
8.6
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 580.9 | 85.6 | 4.0 GB | view |
| 4k | 501.9 | 80.5 | 4.2 GB | view |
| 8k | 520.4 | 75.8 | 4.6 GB | view |
| 16k | 526.3 | 60.7 | 5.3 GB | view |
| 32k | 480.1 | 43.8 | 6.9 GB | view |
| 64k | 368.9 | 21.9 | 8.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.6 | 1.00× |
| 2× | 103.0 | 1.20× |
| 4× | 102.5 | 1.20× |
| 8× | 91.5 | 1.07× |