← Back to community benchmarks
Huihui-A-Next-80B-A3B-Instruct-abliterated
Performance
1k
tokens
1,058
PP tok/s
89.2
TG tok/s
968
TTFT (ms)
43.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,058 | 89.2 | 43.0 GB | current |
| 4k | 1,288 | 82.1 | 43.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 89.2 | 1.00× |
| 2× | 143.2 | 1.61× |
| 4× | 208.3 | 2.34× |
| 8× | 291.0 | 3.26× |