← Back to community benchmarks
Qwopus-GLM-18B-Healed
Performance
1k
tokens
109.3
PP tok/s
11.7
TG tok/s
9373
TTFT (ms)
9.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 109.3 | 11.7 | 9.8 GB | current |
| 4k | 110.7 | 11.4 | 10.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.7 | 1.00× |
| 2× | 22.6 | 1.93× |
| 4× | 26.8 | 2.29× |