← Back to community benchmarks
Qwen3.5-35B-A3B-Hereticmxfp8
Performance
4k
tokens
1,690
PP tok/s
79.3
TG tok/s
2424
TTFT (ms)
35.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,625 | 85.0 | 34.9 GB | view |
| 4k | 1,690 | 79.3 | 35.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.0 | 1.00× |
| 2× | 130.6 | 1.54× |
| 4× | 165.6 | 1.95× |