← Back to community benchmarks
Huihui-Qwen3.5-35B-A3B-abliterated-8bit
Performance
16k
tokens
2,399
PP tok/s
62.2
TG tok/s
6828
TTFT (ms)
37.0
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.10
macOS
macOS 15.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,515 | 73.3 | 36.2 GB | view |
| 4k | 2,667 | 70.8 | 36.3 GB | view |
| 8k | 2,607 | 68.1 | 36.5 GB | view |
| 16k | 2,399 | 62.2 | 37.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.3 | 1.00× |
| 2× | 128.6 | 1.75× |
| 4× | 208.9 | 2.85× |
| 8× | 322.9 | 4.41× |