← Back to community benchmarks
Huihui-Qwen3.5-35B-A3B-abliterated-8bit
Performance
4k
tokens
851.4
PP tok/s
51.6
TG tok/s
4811
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
128 GB
GPU Cores
48
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 821.3 | 53.2 | 36.2 GB | view |
| 4k | 851.4 | 51.6 | 36.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.2 | 1.00× |
| 2× | 92.7 | 1.74× |
| 4× | 135.4 | 2.55× |