← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Engineer-9e-qx64-hi
Performance
4k
tokens
1,850
PP tok/s
84.5
TG tok/s
2215
TTFT (ms)
25.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.13
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,312 | 87.7 | 25.2 GB | view |
| 4k | 1,850 | 84.5 | 25.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 87.7 | 1.00× |
| 2× | 147.8 | 1.69× |
| 4× | 220.1 | 2.51× |