← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
32k
tokens
1,126
PP tok/s
48.5
TG tok/s
29102
TTFT (ms)
38.5
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,091 | 69.6 | 35.4 GB | view |
| 8k | 1,445 | 64.2 | 36.5 GB | view |
| 32k | 1,126 | 48.5 | 38.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 69.6 | 1.00× |
| 2× | 109.8 | 1.58× |