← Back to community benchmarks
GLM-4.7-8bit-gs32
Performance
4k
tokens
236.0
PP tok/s
12.1
TG tok/s
17359
TTFT (ms)
372.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 15.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 221.9 | 13.3 | 370.9 GB | view |
| 4k | 236.0 | 12.1 | 372.4 GB | current |
| 8k | 216.9 | 10.8 | 373.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.3 | 1.00× |
| 8× | 35.0 | 2.63× |