← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
808.5
PP tok/s
57.2
TG tok/s
1267
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 808.5 | 57.2 | 36.2 GB | current |
| 4k | 885.7 | 55.0 | 36.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.2 | 1.00× |
| 2× | 91.3 | 1.60× |
| 4× | 122.3 | 2.14× |
| 8× | 150.6 | 2.63× |