← Back to community benchmarks
Qwen3.5-35B-A3B-Heretic
Performance
1k
tokens
2,018
PP tok/s
53.7
TG tok/s
507
TTFT (ms)
28.1
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,018 | 53.7 | 28.1 GB | current |
| 4k | 2,168 | 52.5 | 28.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.7 | 1.00× |
| 2× | 97.8 | 1.82× |
| 4× | 159.1 | 2.96× |