← Back to community benchmarks
Qwen3.6-35B-A3B-UD-Q8_K_XL
Performance
1k
tokens
488.5
PP tok/s
48.0
TG tok/s
2096
TTFT (ms)
35.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 488.5 | 48.0 | 35.7 GB | current |
| 4k | 611.2 | 46.3 | 36.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.0 | 1.00× |
| 2× | 73.5 | 1.53× |
| 4× | 103.7 | 2.16× |