OpenAI120B~71 GB VRAM at Q4_K_M

GPT-OSS 120B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

OpenAI's first large open-weight release. Dense 120B model at Q4_K_M fits in ~65 GB VRAM — dual RTX 3090 or single A100 80GB. Matches GPT-4o on MMLU (87.4%), MATH (78.9%), and HumanEval (88.5%). The go-to choice for enterprise teams that need GPT-4-class quality without API costs or data privacy concerns.

GPT-OSS 120B needs about 71 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic91
Creative89
Coding89

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
39.5 GB~32 tok/sOffload
Q3_K_M
3.41 bpw
50.9 GB~28 tok/sOffload
Q4_K_M
4.83 bpw
71.6 GB—Too big
Q5_K_M
5.67 bpw
83.9 GB—Too big
Q6_K
6.56 bpw
96.9 GB—Too big
Q8_0
8.50 bpw
125.2 GB—Too big
F16
16.00 bpw
234.7 GB—Too big

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. GPT-OSS 120B VRAM calculator →

Get GPT-OSS 120B running

The cheapest catalogued GPU that runs GPT-OSS 120B is the NVIDIA DGX Spark (128 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
NVIDIA DGX Spark (128GB)
128 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.

How to run GPT-OSS 120B

Install Ollama, then run:

ollama run gpt-oss:120b
Weights on Hugging Face: openai/gpt-oss-120b ↗

Specifications

Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.

Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.

Parameters
116.8B (5.1B active)
Context window
131,072
Architecture
Mixture-of-Experts (128 experts, top-4, MXFP4)
Provider
OpenAI
Licence
Apache 2.0
Practical deployment
Workstation (large unified memory or pro GPU)
Specified at
Q4_K_M
System RAM
128 GB
Record updated
2026-04-01
LicenceApache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forenterpriseprivacy sensitiveon premisegeneral purpose
BenchmarkScoreProvenance
MMLU87.4 / 100 %reported
MATH78.9 / 100 %reported
HumanEval88.5 / 100 %reported

Can I run GPT-OSS 120B on my GPU?

Other GPT-OSS sizes

GPT-OSS 120B — frequently asked questions

How much VRAM does GPT-OSS 120B need?

About 71 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does GPT-OSS 120B run on an RTX 4090 (24 GB)?

No. GPT-OSS 120B needs about 71 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.

How do I run GPT-OSS 120B locally?

Install Ollama and run `ollama run gpt-oss:120b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does GPT-OSS come in?

GPT-OSS 120B (71 GB), GPT-OSS 20B (13 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.