Yes — with 143.4 GB to spare

gpt-oss 120B at MXFP4 fits your CPU only · DDR5 8-channel server entirely on the GPU at 8K context, at an estimated 22 tokens per second. There is room for its full 128K window.

Fully on GPU 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.

What hardware do I need for gpt-oss 120B? →

The VRAM budget

weights 60.5 GB

Weights 60.5 GB KV cache @ 8K 0.29 GB Runtime overhead 0.6 GB Free 143.4 GB of 204.8 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
MXFP4	60.5 GB	61.4 GB	128K	22	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

Ollama llama.cpp LM Studio

terminal

$ llama-server \
    -hf openai/gpt-oss-120b:MXFP4 \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 60.5 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.

02With no GPU, thread count matters more than clock. Start at one thread per physical core.

03There is room to go to the model's full 128K context on this card.

See all models for this rig Compare with another model