← Back to community benchmarks
Huihui-Qwen3.5-35B-A3B-abliterated
Performance
4k
tokens
544.4
PP tok/s
52.5
TG tok/s
7524
TTFT (ms)
27.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.0.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 450.0 | 54.7 | 27.3 GB | view |
| 4k | 544.4 | 52.5 | 27.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.7 | 1.00× |
| 2× | 74.5 | 1.36× |
| 4× | 93.4 | 1.71× |