← Back to community benchmarks
DeepSeek-R1-0528-Qwen3-8B
Performance
1k
tokens
217.4
PP tok/s
12.1
TG tok/s
4711
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 217.4 | 12.1 | 8.7 GB | current |
| 4k | 209.5 | 11.2 | 9.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.1 | 1.00× |
| 2× | 23.8 | 1.97× |
| 4× | 39.0 | 3.22× |