← Back to community benchmarks
Huihui-Qwen3.5-35B-A3B-abliterated-8bit
Performance
4k
tokens
1,733
PP tok/s
81.7
TG tok/s
2363
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,638 | 85.3 | 36.2 GB | view |
| 4k | 1,733 | 81.7 | 36.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.3 | 1.00× |
| 2× | 144.6 | 1.70× |
| 4× | 207.3 | 2.43× |
| 8× | 280.5 | 3.29× |