← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
440.5
PP tok/s
44.4
TG tok/s
9298
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 427.3 | 48.4 | 36.2 GB | view |
| 4k | 440.5 | 44.4 | 36.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.4 | 1.00× |
| 2× | 74.4 | 1.54× |
| 4× | 93.7 | 1.94× |