← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
128k
tokens
815.6
PP tok/s
23.5
TG tok/s
160715
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,846 | 96.2 | 20.1 GB | view |
| 128k | 815.6 | 23.5 | 26.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.2 | 1.00× |
| 2× | 154.4 | 1.60× |
| 4× | 201.2 | 2.09× |
| 8× | 258.9 | 2.69× |