Skip to content
localmodel.run

Text model · gpt-oss

gpt-oss 120B: RAM and VRAM requirements

gpt-oss 120B needs about 62.4 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~59.03 GB to download; KV cache and overhead add the rest), or about 4.2 GB at Q8_0. The lightest hardware that runs it is Apple M4 Max (128GB).

gpt-oss family · 117B params (Mixture-of-Experts: activates only 5.1B of 117B params per token, so generation is faster than the total size suggests) · released Aug 2025.

Shopping for hardware? See what runs gpt-oss 120B →

License Apache-2.0 · Commercial OK ↓ 4.2M/mo ♥ 5.1K on HuggingFace
Q4_K_M GGUF
59.03 GB
Q8_0 GGUF
0.79 GB
Memory @ Q4 (4k)
~62.4 GB
Context
128 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

gpt-oss 120B runs on 4 of 40 tracked devices at Q4_K_M.

4 run well 0 tight fit 36 too small
Fit check Q4_K_M
No, not enough memory
needs 62.4 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)59.03 GB
+
KV cache (4k)2.6 GB
+
Overhead0.8 GB
=
Total62.4 GB

How context length changes it

4k context ~62.4 GB 32k context ~80.6 GB 128k context ~142.9 GB

Longer context grows the KV cache, which for gpt-oss 120B is sized by its 5.1B active params, not the full 117B. It needs ~62.4 GB at 4k and ~142.9 GB at 128k.

Benchmark scores

Aider polyglot · coding

#6 of 10 ranked · Percent of 225 Exercism exercises solved across six languages.

41.8%

Sourced third-party benchmarks for the full-precision gpt-oss 120B, not a specific quant. See the full leaderboard.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 49 GB est
Q3_K_M 57.2 GB est
Q4_K_M (default) 59.03 GB
Q5_K_M 83.4 GB est
Q6_K 95.9 GB est
Q8_0 0.79 GB
FP16 234 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run gpt-oss:120b
llama.cpp
$ llama-cli -hf ggml-org/gpt-oss-120b-GGUF:Q4_K_M
LM Studio
$ lms get ggml-org/gpt-oss-120b-GGUF

Which devices can run gpt-oss 120B?

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

NVIDIA GPUs

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down Command A 111B Next size up Laguna S 2.1 118B

Similar models

Head-to-head

FAQ

How much VRAM or RAM does gpt-oss 120B need?

At Q4_K_M, gpt-oss 120B needs about 62.4 GB (weights ~59.03 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~4.2 GB.

What is the Q4_K_M GGUF file size of gpt-oss 120B?

The Q4_K_M GGUF file is about 59.03 GB to download, and the Q8_0 GGUF is about 0.79 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~62.4 GB of memory at Q4_K_M.

Can gpt-oss 120B run on a laptop?

gpt-oss 120B is large; you need a high-memory Mac or multi-GPU setup at Q4_K_M.

Is gpt-oss 120B cheaper to run because it is a MoE model?

It is faster, not lighter. gpt-oss 120B activates only 5.1B of 117B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 117B.

Can I use gpt-oss 120B commercially?

Yes. gpt-oss 120B is licensed Apache-2.0, which permits commercial use.

Understand the numbers

Short guides to the ideas behind gpt-oss 120B's memory and quant figures.

OpenAI gpt-oss 120B, MoE (5.1B active). Native MXFP4; the official ggml-org GGUF is ~59GB, so it fits an 80GB GPU or a 96GB+ Mac.

Sources

Last validated 2026-08-03. Memory figures are estimates. See methodology.