← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
611.0
PP tok/s
62.5
TG tok/s
6703
TTFT (ms)
19.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.5
macOS
macOS 15.7.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 490.0 | 65.7 | 18.3 GB | view |
| 4k | 611.0 | 62.5 | 19.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.7 | 1.00× |
| 2× | 93.8 | 1.43× |
| 4× | 114.0 | 1.74× |