← Back to community benchmarks
Qwen3.5-35B-A3B4bit-MTP
Performance
32k
tokens
3,082
PP tok/s
85.5
TG tok/s
10631
TTFT (ms)
22.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,698 | 131.8 | 19.2 GB | view |
| 4k | 3,424 | 119.6 | 20.2 GB | view |
| 32k | 3,082 | 85.5 | 22.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 131.8 | 1.00× |
| 2× | 201.6 | 1.53× |
| 4× | 250.7 | 1.90× |
| 8× | 360.9 | 2.74× |