← Back to community benchmarks
gpt-oss-20b-MXFP4-Q8
Performance
16k
tokens
196.2
PP tok/s
16.0
TG tok/s
83522
TTFT (ms)
11.8
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 257.2 | 29.7 | 11.4 GB | view |
| 4k | 262.5 | 26.1 | 11.5 GB | view |
| 8k | 227.1 | 22.6 | 11.6 GB | view |
| 16k | 196.2 | 16.0 | 11.8 GB | current |
| 32k | 150.3 | 2.1 | 12.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.7 | 1.00× |
| 2× | 41.3 | 1.39× |
| 4× | 42.5 | 1.43× |
| 8× | 39.4 | 1.33× |