← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
324.7
PP tok/s
27.0
TG tok/s
12616
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 314.5 | 30.9 | 3.9 GB | view |
| 4k | 324.7 | 27.0 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.9 | 1.00× |
| 2× | 56.1 | 1.82× |
| 4× | 76.0 | 2.46× |
| 8× | 78.8 | 2.55× |