← Back to community benchmarks
Qwen3.6-35B-A3B-oQ8e
Performance
8k
tokens
1,552
PP tok/s
77.1
TG tok/s
5278
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.8.dev3
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,263 | 80.8 | 35.4 GB | view |
| 4k | 1,666 | 80.5 | 36.2 GB | view |
| 8k | 1,552 | 77.1 | 36.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.8 | 1.00× |
| 2× | 135.7 | 1.68× |
| 4× | 192.1 | 2.38× |
| 8× | 251.7 | 3.12× |