← Back to community benchmarks
Qwen2.5-7B-Instruct
Performance
4k
tokens
1,243
PP tok/s
114.2
TG tok/s
3295
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 4k | 1,243 | 114.2 | 4.9 GB | current |
| 8k | 1,225 | 101.0 | 5.3 GB | view |