← Back to community benchmarks
Qwen2.5-Coder-7B-Instruct
Performance
1k
tokens
233.2
PP tok/s
17.6
TG tok/s
4391
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 233.2 | 17.6 | 6.3 GB | current |
| 4k | 210.4 | 16.9 | 6.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.6 | 1.00× |
| 2× | 31.7 | 1.80× |
| 4× | 32.3 | 1.84× |