← Back to community benchmarks
gpt-oss-20b
Performance
1k
tokens
360.3
PP tok/s
52.5
TG tok/s
2842
TTFT (ms)
13.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 360.3 | 52.5 | 13.1 GB | current |
| 4k | 303.4 | 38.6 | 13.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.5 | 1.00× |
| 2× | 39.5 | 0.75× |
| 4× | 52.5 | 1.00× |