← Back to community benchmarks
Huihui-Qwen3.5-35B-A3B-abliterated
Performance
4k
tokens
397.3
PP tok/s
67.6
TG tok/s
10310
TTFT (ms)
18.4
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 429.0 | 59.9 | 18.2 GB | view |
| 4k | 397.3 | 67.6 | 18.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.9 | 1.00× |
| 2× | 93.9 | 1.57× |
| 4× | 103.3 | 1.72× |
| 8× | 108.4 | 1.81× |