← Back to community benchmarks
GLM-5-4bit_副本
Performance
16k
tokens
119.7
PP tok/s
12.9
TG tok/s
136890
TTFT (ms)
402.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.12
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 188.1 | 17.1 | 391.8 GB | view |
| 4k | 181.7 | 14.1 | 394.1 GB | view |
| 8k | 155.6 | 13.7 | 396.7 GB | view |
| 16k | 119.7 | 12.9 | 402.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.1 | 1.00× |
| 2× | 24.6 | 1.44× |
| 4× | 31.5 | 1.84× |
| 8× | 44.1 | 2.58× |