← Back to community benchmarks
Qwen3.5-35B-A3B-Heretic
Performance
1k
tokens
1,055
PP tok/s
49.4
TG tok/s
971
TTFT (ms)
65.6
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,055 | 49.4 | 65.6 GB | current |
| 4k | 1,524 | 48.5 | 66.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.4 | 1.00× |
| 2× | 47.8 | 0.97× |
| 4× | 80.2 | 1.62× |