← Back to community benchmarks
Qwen3.6-35B-A3B-TurboQuant
Performance
16k
tokens
961.0
PP tok/s
51.5
TG tok/s
17049
TTFT (ms)
16.9
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 776.6 | 68.6 | 15.2 GB | view |
| 4k | 1,119 | 65.1 | 16.0 GB | view |
| 8k | 1,097 | 60.2 | 16.3 GB | view |
| 16k | 961.0 | 51.5 | 16.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 68.6 | 1.00× |
| 2× | 88.7 | 1.29× |