§01·compatibility · /check

gpt-oss 20B on Apple M3 Max

Yes — a published step-by-step recipe documents running gpt-oss 20B on the Apple M3 Max (48 GB). Community benchmark numbers aren't seeded yet, so measured speed and peak VRAM aren't shown.

✓ recipellmactiveapple series48GB VRAM

model

name: gpt-oss 20B
slug: gpt-oss-20b
vertical: llm
status: active
repo: huggingface.co ↗

open detail ↗

gpu

name: Apple M3 Max
slug: m3-max
vram: 48 GB
series: apple

open detail ↗

§02·benchmarks

No verified benchmarks yet. Be the first to contribute one.

§03·common questions

Can you run gpt-oss 20B on Apple M3 Max?

Yes — a published step-by-step recipe documents running gpt-oss 20B on the Apple M3 Max (48 GB). Community benchmark numbers aren't seeded yet, so measured speed and peak VRAM aren't shown.

Are there step-by-step instructions for gpt-oss 20B on Apple M3 Max?

Yes — a step-by-step recipe documents gpt-oss 20B on the Apple M3 Max; see the recipes listed below.

§04·related recipes

gpt-oss 20B on Apple M3 Max

gpt-oss 20B on Apple M3 Max: native-MXFP4 chat in 48 GB unified memory with MLX

gpt-oss 20B on Apple M4 Max: native-MXFP4 chat in 48 GB unified memory with MLX

gpt-oss 20B on Apple M2 Max: native-MXFP4 chat in 64 GB unified memory with MLX

gpt-oss 20B on RX 7800 XT: MXFP4 chat in 16 GB via Ollama or llama.cpp-HIP

gpt-oss 20B on RX 7900 XTX: MXFP4 chat at ~119 tok/s via Ollama or llama.cpp-HIP