GPT-OSS Models — Hardware Requirements
14 GPT-OSS models from OpenAI and the community, from the smallest that runs in 12.6 GB of VRAM at Q4 up to 120B parameters. Every row links to full quantization tables and GPU compatibility.
All GPT-OSS Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| GPT OSS 20B | 20.9B | 13.1 GB | 131K | ||
| InternVL3 5 GPT OSS 20B A4B Preview HF | 21.2B | 13.6 GB | 131K | ||
| GPT OSS Safeguard 20B | 21.5B | 13.5 GB | 131K | ||
| GPT OSS 120B | 116.8B | 70.8 GB | 131K | ||
| GPT OSS 120B DFlash | 120B | 72.5 GB | 131K |
Community variants and fine-tunes(7)
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| GPT OSS 20B NPU2 | 20B | 12.6 GB | 131K | ||
| Huihui GPT OSS 20B BF16 Abliterated | 20.9B | 13.1 GB | 131K | ||
| GPT OSS 20B RichardErkhov Heresy | 20.9B | 13.1 GB | 131K | ||
| GPT OSS 20B Heretic | 20.9B | 13.1 GB | 131K | ||
| GPT OSS 20B Heretic Ara v3 | 21.5B | 13.5 GB | 131K | ||
| GPT OSS 120B Eagle3 Short Context | 120B | 72.3 GB | 131K | ||
| GPT OSS 120B Eagle3 v3 | 120B | 72.3 GB | 131K |
How GPT-OSS Compares — llmrun Composite Score
GPT OSS 120B is the highest-scoring GPT-OSS model with an llmrun Composite Score of 97.5 — #66 among 106 open models. The top proprietary model, Gemini 4 Carbon, scores 158.6. Click a model to see its full benchmark breakdown.
Gemini 4 Carbon · proprietary158.6
GPT 6 Astra · proprietary156.2
Claude Opus 5.5 · proprietary153.0
GPT 6.1 Sol · proprietary151.7
GPT 6.1 Terra · proprietary150.1
Kimi K3.1 Pro142.8
MiMo V2.6 Pro RL133.3
Kimi K3132.7
MiMo V2.6 Flash RL131.9
GLM 5.3130.1
DeepSeek V4.1 Flash129.4
DeepSeek V4 Pro 0813129.2
GPT OSS 120B97.5
GPT OSS 20B96.4
Frequently Asked Questions
- How much VRAM do I need to run a GPT-OSS model?
- The smallest GPT-OSS model, GPT OSS 20B NPU2, runs from 12.6 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 8.9 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which GPT-OSS models can I run on a 16 GB GPU?
- 8 of 12 GPT-OSS models fit in 16 GB of VRAM at Q4_K_M, including GPT OSS 20B, Huihui GPT OSS 20B BF16 Abliterated, GPT OSS 20B RichardErkhov Heresy.
- What is the most popular GPT-OSS model to run locally?
- GPT OSS 20B is the most downloaded GPT-OSS model in local-friendly quantized formats. It runs from 13.1 GB of VRAM at Q4_K_M.
- How do GPT-OSS models score on benchmarks?
- GPT OSS 120B leads the family with an llmrun Composite Score of 97.5, ranking #66 among 106 open models, while the top proprietary model, Gemini 4 Carbon, scores 158.6. See the comparison chart above for the full standings.