← Back to community benchmarks
GLM-4.6V-5bit
Performance
16k
tokens
481.8
PP tok/s
24.3
TG tok/s
34008
TTFT (ms)
74.0
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 618.2 | 37.5 | 71.1 GB | view |
| 4k | 654.1 | 33.8 | 71.8 GB | view |
| 8k | 591.7 | 29.7 | 72.6 GB | view |
| 16k | 481.8 | 24.3 | 74.0 GB | current |
| 32k | 350.2 | 17.8 | 76.9 GB | view |
| 64k | 226.2 | 11.6 | 82.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.5 | 1.00× |
| 2× | 53.2 | 1.42× |
| 4× | 74.1 | 1.98× |
| 8× | 83.7 | 2.23× |