← Back to community benchmarks
DeepSeek-R1-0528-Qwen3-8B
Performance
1k
tokens
220.6
PP tok/s
21.8
TG tok/s
4642
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.0rc1
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 220.6 | 21.8 | 4.9 GB | current |
| 4k | 210.0 | 19.3 | 5.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.8 | 1.00× |
| 2× | 42.2 | 1.94× |
| 4× | 52.9 | 2.43× |