← Back to community benchmarks
Qwen2.5-Coder-3B-Instruct
Performance
1k
tokens
2,604
PP tok/s
172.7
TG tok/s
393
TTFT (ms)
2.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
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 | 2,604 | 172.7 | 2.4 GB | current |
| 4k | 3,350 | 151.1 | 2.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 172.7 | 1.00× |
| 2× | 310.0 | 1.80× |
| 4× | 474.3 | 2.75× |