← Back to community benchmarks
Qwen3___6-35B-A3B
Performance
4k
tokens
461.6
PP tok/s
44.4
TG tok/s
8873
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
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 | 419.2 | 47.0 | 19.2 GB | view |
| 4k | 461.6 | 44.4 | 19.9 GB | current |
| 8k | 448.3 | 39.2 | 20.2 GB | view |
| 16k | 411.8 | 21.2 | 20.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.0 | 1.00× |
| 2× | 71.1 | 1.51× |