← Back to community benchmarks
Huihui-Qwen3.5-35B-A3B-abliterated-4bit
Performance
64k
tokens
416.9
PP tok/s
23.2
TG tok/s
157208
TTFT (ms)
23.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 572.7 | 63.4 | 20.1 GB | view |
| 4k | 594.2 | 60.2 | 20.2 GB | view |
| 8k | 583.1 | 56.9 | 20.4 GB | view |
| 16k | 559.9 | 46.6 | 20.8 GB | view |
| 32k | 512.8 | 34.7 | 21.6 GB | view |
| 64k | 416.9 | 23.2 | 23.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.4 | 1.00× |
| 2× | 92.2 | 1.45× |
| 4× | 117.3 | 1.85× |
| 8× | 131.3 | 2.07× |