← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
1,129
PP tok/s
71.5
TG tok/s
7259
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
128 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,095 | 78.2 | 20.1 GB | view |
| 4k | 1,148 | 76.1 | 20.2 GB | view |
| 8k | 1,129 | 71.5 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 78.2 | 1.00× |
| 2× | 132.2 | 1.69× |
| 4× | 194.3 | 2.48× |