← Back to community benchmarks
Qwen3.6-35B-A3BoQ4
Performance
16k
tokens
916.4
PP tok/s
51.2
TG tok/s
17879
TTFT (ms)
21.8
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8.dev1
macOS
macOS 26.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 732.7 | 64.1 | 20.1 GB | view |
| 4k | 961.0 | 60.7 | 20.9 GB | view |
| 8k | 969.3 | 56.9 | 21.2 GB | view |
| 16k | 916.4 | 51.2 | 21.8 GB | current |
| 32k | 798.6 | 42.6 | 23.2 GB | view |
| 64k | 568.4 | 29.8 | 25.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.1 | 1.00× |
| 2× | 95.5 | 1.49× |