← Back to community benchmarks
Qwen3.6-35B-A3B-Holo3-Qwopus-Instruct-qx64-hi
Performance
4k
tokens
1,303
PP tok/s
60.5
TG tok/s
3143
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 832.5 | 62.2 | 28.9 GB | view |
| 4k | 1,303 | 60.5 | 29.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.2 | 1.00× |
| 2× | 106.5 | 1.71× |
| 4× | 167.2 | 2.69× |
| 8× | 215.1 | 3.46× |