← Back to community benchmarks
Huihui-Qwen3.5-35B-A3B-abliterated
Performance
4k
tokens
1,326
PP tok/s
40.4
TG tok/s
3088
TTFT (ms)
28.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 15.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,035 | 41.6 | 28.4 GB | view |
| 4k | 1,326 | 40.4 | 28.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.6 | 1.00× |
| 2× | 75.4 | 1.81× |
| 4× | 119.3 | 2.87× |
| 8× | 170.1 | 4.09× |