← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
597.7
PP tok/s
64.2
TG tok/s
6853
TTFT (ms)
20.0
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 493.5 | 67.9 | 19.3 GB | view |
| 4k | 597.7 | 64.2 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 67.9 | 1.00× |
| 2× | 95.3 | 1.40× |
| 4× | 116.8 | 1.72× |