← Back to community benchmarks
Qwen3.6-35B-A3B-Uncensored-Heretic
Performance
1k
tokens
2,039
PP tok/s
95.0
TG tok/s
502
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.5.dev1
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,039 | 95.0 | 19.2 GB | current |
| 4k | 2,194 | 92.3 | 20.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.0 | 1.00× |
| 2× | 146.3 | 1.54× |
| 4× | 198.5 | 2.09× |