Yes — GPT-oss 20B (21B-A3.6B) runs at 103 tok/s on M5 Max with 64 GB RAM using MXFP4 quantization via MLX. A capable open-source LLM with 21B-A3.6B parameters.
Want to run GPT-oss 20B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates GPT-oss 20B on M5 Max using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →
| Metric | Value |
|---|---|
| Tokens per second | 103 tok/s |
| Time to first token | — |
| Quantization | MXFP4 |
| Minimum RAM | 64 GB |
| Recommended engine | MLX |
| Parameters | 21B-A3.6B |
| Benchmark date | 2026-10 |
MXFP4 21B-A3.6B MLX M5 Max
The recommended engine for GPT-oss 20B on M5 Max is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
To run GPT-oss 20B on M5 Max you need:
GPT-oss 20B needs about 64 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how GPT-oss 20B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard