← Back to community benchmarks
FuseO1-DeepSeekR1-Qwen2.5-Coder-14B-Preview-mixed_3_6
Performance
4k
tokens
244.2
PP tok/s
28.7
TG tok/s
16773
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 246.2 | 32.5 | 7.2 GB | view |
| 4k | 244.2 | 28.7 | 7.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.5 | 1.00× |
| 2× | 42.6 | 1.31× |
| 4× | 41.9 | 1.29× |