← Back to community benchmarks
gpt-oss-20b-reap-0.4-mxfp4
Performance
4k
tokens
1,253
PP tok/s
81.7
TG tok/s
3269
TTFT (ms)
8.3
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7rc2
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,069 | 87.2 | 8.2 GB | view |
| 4k | 1,253 | 81.7 | 8.3 GB | current |
| 16k | 1,046 | 57.5 | 8.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 87.2 | 1.00× |
| 2× | 103.0 | 1.18× |
| 4× | 151.3 | 1.74× |