← Back to community benchmarks
Qwen3.6-35B-A3B-TurboQuant
Performance
1k
tokens
427.2
PP tok/s
69.0
TG tok/s
2397
TTFT (ms)
11.1
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 427.2 | 69.0 | 11.1 GB | current |
| 4k | 461.7 | 64.1 | 11.9 GB | view |
| 8k | 446.4 | 56.9 | 12.3 GB | view |
| 16k | 408.9 | 49.1 | 13.1 GB | view |
| 32k | 338.5 | 37.1 | 14.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 69.0 | 1.00× |
| 2× | 83.7 | 1.21× |
| 4× | 84.8 | 1.23× |