Home / Models / gpt-oss-120b

How to Run gpt-oss-120b Locally — Setup Guide (August 2026)

gpt-oss-120b is OpenAI's open-weight frontier-class reasoning model — a 120B-parameter Mixture-of-Experts that activates only ~5B parameters per token, native in the MXFP4 format. That low active-parameter count is exactly what lets a single 24 GB card run it.

Numbers you can trust

We don't print guessed speeds. Every measured number on this page came from TurboLLM's own auto-tuner running gpt-oss-120b on real hardware — labeled as such. When you run it yourself, TurboLLM benchmarks it on your exact GPU and shows a VRAM-fit verdict before you load, and the real measured tokens/sec once it's running.

Does it fit your GPU?

Only a handful of the 120B total parameters activate per token. Keep attention and the KV cache in VRAM, park the idle experts in system RAM, and the GPU only ever has to touch a small active slice — a dense 120B model offloaded the same way would crawl.

gpt-oss-120b
OpenAI · GGUF
MoE · ~5B active
toolsthinkingcode
VRAMFit
24 GB+MXFP4 (~63 GB), experts offloaded to system RAM — auto-fit sets it up · 128K context
ggml-org/gpt-oss-120b-GGUF
View on Hugging Face →

How to run it

  1. Install TurboLLM

    npx turbollm — no install step, works on Windows, macOS, and Linux. It detects your GPU and auto-provisions a matching llama-server build (no CUDA toolkit, no Python, no compiler).

  2. Get the model

    Paste ggml-org/gpt-oss-120b-GGUF into TurboLLM's in-app Hugging Face search — it lists every quant with a VRAM-fit verdict against your real free VRAM, and downloads are resumable and SHA-256 verified.

  3. Let auto-fit pick the setup

    Flip the auto-fit toggle and TurboLLM chooses the GPU/CPU layer split (and, for a Mixture-of-Experts model, the expert-offload split) for your card — the same manual flag-hunting every other guide walks you through by hand.

  4. Load it

    TurboLLM benchmarks the model on your exact GPU as it loads and shows the real measured tokens/sec — not a number copied from someone else's card.

  5. Use it

    Chat in the built-in UI, or point any OpenAI- or Anthropic-compatible tool (including Claude Code) at TurboLLM's local API — see the API docs.

FAQ

Why does gpt-oss-120b suddenly get slow or stutter?

The usual cause is silent VRAM spill: once a model's weights plus its KV cache stop fitting in VRAM, the driver quietly offloads the overflow to system RAM over PCIe, and that path runs 5–10× slower with no error message — just a sudden slowdown. TurboLLM's auto-fit sizes the quant and GPU/CPU split against your card's real free VRAM (including KV-cache growth at your chosen context) specifically to avoid this, and shows a VRAM-fit verdict before you load rather than after it's already crawling. Full mechanics in VRAM spill explained.

Which quant should I use for gpt-oss-120b?

Pick the highest quant that fits your VRAM with room left over for the KV cache and compute buffer — not just the model weights. As a starting point, Q4_K_M is usually the sweet spot (small quality loss for a large size drop); step up to Q5_K_M/Q6_K/Q8_0 if you have headroom, or down to Q3_K_M/an IQ quant if you don't. TurboLLM shows a VRAM-fit verdict for every quant against your card's real free VRAM before you download — see Quantization explained for what the letters and numbers actually mean, or llama.cpp flags that actually matter for the other settings worth knowing.

Will gpt-oss-120b run on my GPU?

Check the VRAM table above for the tier closest to your card. If you're not sure which tier you're in, or want picks tailored to your exact hardware, use What can I run? — enter your VRAM (or Apple unified memory) and it suggests the model, quant, and offload split that fits, the same logic TurboLLM's auto-fit runs when you load a model.

How is running gpt-oss-120b on TurboLLM different from Ollama or LM Studio?

All three can run gpt-oss-120b as a GGUF. The differences show up around the edges: TurboLLM auto-tunes the quant and GPU/CPU split against your card's measured free VRAM rather than a fixed default, shows real generation speed instead of a guess, and lets you add a community fork — like the one behind this page, where relevant — without compiling anything yourself. Ollama and LM Studio each ship one blessed runtime you can't swap out. If your current setup already works well for you, there's no need to switch.

Run it now

$ npx turbollm

One command detects your GPU, provisions the right engine, and opens the UI. New here? Start with Install & first run and Quantization explained. On different hardware, see RTX 4090 or RTX 3090. Also see how to run it.