← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
2,103
PP tok/s
87.3
TG tok/s
3896
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 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 | 2,097 | 96.9 | 20.1 GB | view |
| 4k | 2,173 | 92.9 | 20.2 GB | view |
| 8k | 2,103 | 87.3 | 20.4 GB | current |
| 16k | 1,940 | 77.7 | 20.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.9 | 1.00× |
| 2× | 165.7 | 1.71× |
| 4× | 261.6 | 2.70× |
| 8× | 374.4 | 3.86× |