← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
540.9
PP tok/s
52.3
TG tok/s
15144
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 507.9 | 59.9 | 19.3 GB | view |
| 4k | 601.9 | 56.9 | 20.0 GB | view |
| 8k | 540.9 | 52.3 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.9 | 1.00× |
| 2× | 87.8 | 1.47× |
| 4× | 110.4 | 1.84× |
| 8× | 131.8 | 2.20× |