← Back to community benchmarks
Qwen3.6-35B
Performance
128k
tokens
1,398
PP tok/s
56.0
TG tok/s
93732
TTFT (ms)
46.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,132 | 99.4 | 35.4 GB | view |
| 4k | 3,263 | 98.9 | 36.1 GB | view |
| 8k | 3,586 | 95.8 | 36.5 GB | view |
| 16k | 3,508 | 93.1 | 37.1 GB | view |
| 32k | 3,070 | 86.4 | 38.5 GB | view |
| 64k | 2,356 | 74.2 | 41.1 GB | view |
| 128k | 1,398 | 56.0 | 46.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 99.4 | 1.00× |
| 2× | 150.6 | 1.52× |