← Back to community benchmarks
gpt-oss-20b
Performance
4k
tokens
904.2
PP tok/s
68.3
TG tok/s
4530
TTFT (ms)
13.1
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 4k | 904.2 | 68.3 | 13.1 GB | current |
| 8k | 891.4 | 63.1 | 13.2 GB | view |