← Back to community benchmarks
Qwen3.5-35B-A3B-Heretic
Performance
1k
tokens
850.6
PP tok/s
88.6
TG tok/s
1204
TTFT (ms)
18.6
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 850.6 | 88.6 | 18.6 GB | current |
| 4k | 891.8 | 83.1 | 18.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 88.6 | 1.00× |
| 2× | 136.9 | 1.55× |
| 4× | 174.0 | 1.96× |