← Back to community benchmarks
Huihui-Qwen3.5-35B-A3B-abliterated
Performance
64k
tokens
415.6
PP tok/s
8.4
TG tok/s
157679
TTFT (ms)
21.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 484.8 | 64.5 | 18.3 GB | view |
| 4k | 595.8 | 62.6 | 18.4 GB | view |
| 8k | 597.8 | 45.4 | 18.6 GB | view |
| 16k | 577.3 | 31.3 | 19.0 GB | view |
| 32k | 524.7 | 17.3 | 19.9 GB | view |
| 64k | 415.6 | 8.4 | 21.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.5 | 1.00× |
| 2× | 91.4 | 1.42× |
| 4× | 113.4 | 1.76× |