← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4
Performance
4k
tokens
314.2
PP tok/s
44.5
TG tok/s
13036
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 282.9 | 39.5 | 19.9 GB | view |
| 4k | 314.2 | 44.5 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.5 | 1.00× |
| 2× | 59.2 | 1.50× |
| 4× | 60.6 | 1.53× |