← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
400.5
PP tok/s
38.2
TG tok/s
10228
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 386.6 | 40.5 | 20.0 GB | view |
| 4k | 400.5 | 38.2 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.5 | 1.00× |
| 2× | 61.6 | 1.52× |
| 4× | 64.4 | 1.59× |