← Back to community benchmarks
OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi
Performance
16k
tokens
347.6
PP tok/s
23.8
TG tok/s
47129
TTFT (ms)
12.1
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.7
macOS
macOS 15.7.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 342.4 | 33.3 | 11.8 GB | view |
| 4k | 382.9 | 31.6 | 11.9 GB | view |
| 8k | 374.8 | 29.4 | 12.0 GB | view |
| 16k | 347.6 | 23.8 | 12.1 GB | current |
| 32k | 300.8 | 18.0 | 12.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.3 | 1.00× |
| 2× | 46.3 | 1.39× |
| 4× | 54.9 | 1.65× |