GPT-oss 120B — VRAM Requirements
Written by Jakub Rusinowski · Last updated April 1, 2026
How much GPU VRAM you need to run GPT-OSS GPT-oss 120B by OpenAI locally, a 116.8B-parameter model. Figures are quantized weights + KV cache + framework overhead, computed from the model's parameter count and published architecture — not a throughput model. See /en/methodology.
GPT-oss 120B needs about 72 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 38.4 GB | 39.8 GB |
| Q3_K_M | 3.41 | 49.8 GB | 51.2 GB |
| Q4_K_M | 4.83 | 70.5 GB | 71.9 GB |
| Q5_K_M | 5.67 | 82.8 GB | 84.2 GB |
| Q6_K | 6.56 | 95.8 GB | 97.2 GB |
| Q8_0 | 8.50 | 124.1 GB | 125.5 GB |
| F16 | 16.00 | 233.6 GB | 235.0 GB |
Switch quantization in the interactive calculator, or see the full GPT-OSS model page.
or compare on Vast.ai from $0.77/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Add this badge to your model card
Model creators: paste this into your Hugging Face model card README to link readers straight to this VRAM breakdown.
[](https://llmconfigurator.com/en/vram-calculator/gpt-oss-120b-full?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=gpt-oss-120b-full)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.