← Back to community benchmarks
Huihui-GLM-4.7-Flash-abliterated
Performance
1k
tokens
1,182
PP tok/s
83.5
TG tok/s
866
TTFT (ms)
16.4
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 | 1,182 | 83.5 | 16.4 GB | current |
| 4k | 1,103 | 74.6 | 17.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 83.5 | 1.00× |
| 2× | 131.6 | 1.58× |
| 4× | 177.4 | 2.12× |
| 8× | 211.1 | 2.53× |