← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
1,393
PP tok/s
120.8
TG tok/s
735
TTFT (ms)
19.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,393 | 120.8 | 19.3 GB | current |
| 4k | 1,735 | 115.6 | 20.0 GB | view |
| 8k | 1,724 | 109.0 | 20.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 120.8 | 1.00× |
| 2× | 196.4 | 1.63× |