← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,404
PP tok/s
104.1
TG tok/s
2917
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.4
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,107 | 109.3 | 19.2 GB | view |
| 4k | 1,404 | 104.1 | 20.0 GB | current |
| 8k | 1,396 | 96.6 | 20.4 GB | view |
| 16k | 1,303 | 85.9 | 21.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 109.3 | 1.00× |
| 2× | 170.4 | 1.56× |
| 4× | 226.3 | 2.07× |