← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
1,669
PP tok/s
95.2
TG tok/s
4908
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,269 | 104.8 | 19.3 GB | view |
| 4k | 1,643 | 100.1 | 20.0 GB | view |
| 8k | 1,669 | 95.2 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 104.8 | 1.00× |
| 2× | 177.1 | 1.69× |
| 4× | 261.4 | 2.49× |