← Back to community benchmarks
Qwen2.5-Coder-7B-Instruct
Performance
4k
tokens
137.7
PP tok/s
13.4
TG tok/s
29739
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 142.5 | 14.3 | 4.5 GB | view |
| 4k | 137.7 | 13.4 | 4.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.3 | 1.00× |
| 2× | 26.5 | 1.85× |
| 4× | 28.2 | 1.97× |