← Back to community benchmarks
GLM-4.7-Flash-Derestricted-8bit-gs32
Performance
1k
tokens
1,168
PP tok/s
49.3
TG tok/s
877
TTFT (ms)
32.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.24
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,168 | 49.3 | 32.0 GB | current |
| 4k | 1,265 | 43.6 | 33.0 GB | view |
| 8k | 1,001 | 37.6 | 34.6 GB | view |
| 16k | 663.2 | 31.4 | 36.6 GB | view |
| 32k | 386.8 | 23.2 | 43.8 GB | view |
| 64k | 207.1 | 15.1 | 56.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.3 | 1.00× |
| 2× | 68.8 | 1.40× |
| 4× | 84.9 | 1.72× |