← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
703.1
PP tok/s
48.3
TG tok/s
23302
TTFT (ms)
37.0
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.10
macOS
macOS 26.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 666.6 | 62.1 | 36.2 GB | view |
| 4k | 739.6 | 61.2 | 36.3 GB | view |
| 8k | 736.6 | 57.3 | 36.5 GB | view |
| 16k | 703.1 | 48.3 | 37.0 GB | current |
| 32k | 636.9 | 34.3 | 37.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.1 | 1.00× |
| 2× | 101.7 | 1.64× |
| 4× | 145.3 | 2.34× |