← Back to community benchmarks
qwen3.5-9b-oQ4e
Performance
1k
tokens
1,865
PP tok/s
95.6
TG tok/s
549
TTFT (ms)
6.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,865 | 95.6 | 6.1 GB | current |
| 4k | 2,715 | 91.2 | 6.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.6 | 1.00× |
| 2× | 165.5 | 1.73× |
| 4× | 202.7 | 2.12× |
| 8× | 212.4 | 2.22× |