← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,471
PP tok/s
96.4
TG tok/s
2785
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,167 | 102.0 | 19.2 GB | view |
| 4k | 1,471 | 96.4 | 19.4 GB | current |
| 8k | 1,465 | 91.4 | 19.6 GB | view |
| 16k | 1,329 | 75.2 | 20.0 GB | view |
| 32k | 997.0 | 45.9 | 20.8 GB | view |
| 64k | 679.6 | 29.6 | 22.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 102.0 | 1.00× |
| 2× | 88.7 | 0.87× |
| 4× | 203.3 | 1.99× |
| 8× | 251.5 | 2.47× |