← Back to community benchmarks
gpt-oss-20b
Performance
4k
tokens
302.0
PP tok/s
42.8
TG tok/s
13563
TTFT (ms)
13.1
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.9
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 263.1 | 47.2 | 13.1 GB | view |
| 4k | 302.0 | 42.8 | 13.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.2 | 1.00× |
| 2× | 37.2 | 0.79× |
| 4× | 55.1 | 1.17× |