Yes, just — 10.6 GB spare
gpt-oss 120B at MXFP4 fits your M2 Max · 96 GB entirely in unified memory at 8K context, at an estimated 39 tokens per second. There is room for its full 128K window.
Fully in unified memory
8K context
MXFP4 · 60.5 GB
Apache 2.0
Released Aug 2025
Native MXFP4
Designed to land on one 80 GB card. Only ~5B parameters are active per token.
The VRAM budget
weights 60.5 GB
Weights 60.5 GB
KV cache @ 8K 0.29 GB
Runtime overhead 0.6 GB
Free 10.6 GB of 72.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| MXFP4 | 60.5 GB | 61.4 GB | 128K | 39 | 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-120b-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
01Download is 60.5 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 72.0 GB of 96 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03Only 10.6 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 128K context.