OpenAI gpt-oss-20b
OpenAI · GPT-OSS
OpenAI's first commercially-licensed open-weight model — a historic release under Apache 2.0. MoE architecture keeps only 3.6B parameters active at inference, so it generates tokens at nearly 7B speed despite 20B total params. Supports function calling and web browsing. Over 10M downloads across Ollama and HuggingFace. Pull it with ollama run gpt-oss:20b.
Params
20B total / 3.6B active (MoE)
License
Apache 2.0
Context
128K
Min VRAM
12 GB
Min RAM
16 GB
Tier
Standard
Run locally with Ollama
ollama run gpt-oss:20bOnce running, Ollama exposes an OpenAI-compatible endpoint at localhost:11434/v1.
Will it run on my hardware?
OpenAI gpt-oss-20b needs about 12 GB of fast memory at Q4. Here is what in our hardware database clears that bar.
Runs at full speed · 12
Runs, but slower on shared memory · 3
Hardware links are affiliate links. We earn a small commission if you buy through them — at no extra cost to you. Disclosure
Specifications
| Parameters | 20B total / 3.6B active (MoE) |
|---|---|
| Active params (MoE) | 3.6B active per token |
| Context window | 128K |
| License | Apache 2.0 |
| Min VRAM (Q4) | 12 GB |
| Min RAM | 16 GB |
| Recommended tier | Standard |
| Best for | chatcodingreasoningtool use |
Variants on Ollama
Ollama serves the Q4_K_M quantization by default. Higher-precision tags exist for users with more memory.
OpenAI gpt-oss-20b
ollama run gpt-oss:20bollama pull gpt-oss:q8_0ollama pull gpt-oss:fp16Exact quantization tags vary per model — run ollama show gpt-oss or check the tags page for the full list.
Popularity trend (illustrative)
Illustrative adoption trend, not actual download counts. We do not publish a download number for any model because we have no honest source for it.
Similar models
Qwen3 8B
Alibaba · Apache 2.0
One of the most-downloaded mid-size AI models on HuggingFace in 2026, with tens of millions of downloads. Qwen3 8B outperforms the previous Qwen2.5 14B on most benchmarks, supports hybrid thinking mode and tool calling, and runs on any GPU with 6 GB VRAM. Apache 2.0 license — fully commercial.
Min VRAM
5 GB
Context
128K
Run with Ollama
ollama run qwen3:8bGemma 4 12B
Google · Apache 2.0
Google's latest Gemma generation doubles the context window to 256K tokens and — a major shift from earlier Gemma releases — ships under the Apache 2.0 license. The 12B model is one of the most actively fine-tuned coding bases on HuggingFace in 2026, with hundreds of community GGUF variants. Runs on any GPU with 10 GB VRAM.
Min VRAM
8 GB
Context
256K
Run with Ollama
ollama run gemma4:12bPhi-4 14B
Microsoft · MIT
Microsoft's research-driven Phi-4 focuses on synthetic high-quality training data, producing a 14B model that outperforms much larger models on coding and mathematical reasoning benchmarks. MIT licensed with zero usage restrictions for commercial projects.
Min VRAM
8 GB
Context
16K
Run with Ollama
ollama run phi4:14b