← Back to community benchmarks
gpt-oss-20b-MXFP4-Q8
Performance
32k
tokens
251.4
PP tok/s
21.2
TG tok/s
130336
TTFT (ms)
13.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 318.7 | 31.6 | 11.4 GB | view |
| 4k | 327.7 | 31.1 | 11.7 GB | view |
| 32k | 251.4 | 21.2 | 13.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.6 | 1.00× |
| 2× | 46.5 | 1.47× |
| 4× | 54.1 | 1.71× |