← Back to community benchmarks
gpt-oss-20b-MXFP4-Q8
Performance
1k
tokens
1,458
PP tok/s
124.5
TG tok/s
703
TTFT (ms)
11.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,458 | 124.5 | 11.8 GB | current |
| 4k | 3,424 | 110.2 | 11.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 124.5 | 1.00× |
| 2× | 168.5 | 1.35× |
| 4× | 220.4 | 1.77× |