← Back to community benchmarks
Qwen3.5-4B
Performance
8k
tokens
193.8
PP tok/s
27.9
TG tok/s
42277
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 201.8 | 32.3 | 3.9 GB | view |
| 4k | 199.8 | 29.4 | 4.2 GB | view |
| 8k | 193.8 | 27.9 | 4.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.3 | 1.00× |
| 2× | 44.8 | 1.39× |
| 4× | 47.1 | 1.46× |
| 8× | 40.2 | 1.24× |