← Back to community benchmarks
Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-source-oQ4-fp16-mtp
Performance
4k
tokens
661.9
PP tok/s
60.6
TG tok/s
6189
TTFT (ms)
40.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 667.2 | 63.9 | 39.7 GB | view |
| 4k | 661.9 | 60.6 | 40.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.9 | 1.00× |
| 2× | 100.8 | 1.58× |
| 4× | 113.6 | 1.78× |