Yes — with 372.4 GB to spare
gpt-oss 20B at MXFP4 fits your M3 Ultra · 512 GB entirely in unified memory at 8K context, at an estimated 112 tokens per second. There is room for its full 128K window.
Fully in unified memory
8K context
MXFP4 · 10.8 GB
Apache 2.0
Released Aug 2025
Native MXFP4
Ships natively in MXFP4, so the 4-bit weights are the reference weights, not a lossy copy. Fits 16 GB.
The VRAM budget
weights 10.8 GB
Weights 10.8 GB
KV cache @ 8K 0.19 GB
Runtime overhead 0.6 GB
Free 372.4 GB of 384.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| MXFP4 | 10.8 GB | 11.6 GB | 128K | 112 | Reference | Recommended |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (128 tokens, 1 global in 2), which is why its cache barely grows with context.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/gpt-oss-20b-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
01Download is 10.8 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 384.0 GB of 512 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 128K context on this card.