← Back to community benchmarks
Qwen3.6-35B-A3B-oQ5
Performance
1k
tokens
475.7
PP tok/s
56.0
TG tok/s
2152
TTFT (ms)
23.9
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 475.7 | 56.0 | 23.9 GB | current |
| 4k | 573.5 | 53.5 | 24.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.0 | 1.00× |
| 2× | 79.4 | 1.42× |
| 4× | 99.0 | 1.77× |