← Back to community benchmarks
Qwen3.5-35B-A3B-Heretic
Performance
4k
tokens
891.7
PP tok/s
58.6
TG tok/s
4594
TTFT (ms)
18.8
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
128 GB
GPU Cores
48
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 856.5 | 61.3 | 18.6 GB | view |
| 4k | 891.7 | 58.6 | 18.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.3 | 1.00× |
| 2× | 98.0 | 1.60× |
| 4× | 140.7 | 2.30× |