← Back to community benchmarks
Qwen3.5-4B-OptiQ
Performance
16k
tokens
191.7
PP tok/s
13.5
TG tok/s
85480
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 196.4 | 19.2 | 4.8 GB | view |
| 4k | 209.0 | 19.4 | 5.4 GB | view |
| 8k | 201.8 | 17.7 | 5.7 GB | view |
| 16k | 191.7 | 13.5 | 6.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.2 | 1.00× |
| 2× | 33.9 | 1.77× |
| 4× | 38.7 | 2.02× |