Gpt Oss Nano needs about 7.7 GB of memory at Q4_K_M (a 6.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 9.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Compact 9B GPT-OSS model with Mixture of Experts for step‑by‑step reasoning
GPT‑OSS‑Nano is a fine‑tuned Mixture of Experts language model built on the GPT‑OSS architecture. It is optimized for chain‑of‑thought reasoning and problem solving, using only ~3B active parameters per forward pass.
Good at
- Step‑by‑step reasoning
- Problem solving
- Chain‑of‑thought generation
Limits
- Limited to English, multilingual performance varies
- May hallucinate on obscure topics
- Not suitable for safety‑critical use
Best for
- Short‑form reasoning tasks
- Educational tutoring
- Code debugging assistance
Who it’s for. Developers and researchers who need a lightweight reasoning model for local inference. The model is released under Apache 2.0 and can be run with llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ1_M | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ1_S | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ2_XXS | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ2_XS | 5.3 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_S | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ2_M | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ2_S | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ3_S | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ3_XS | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ3_XXS | 5.3 GB | 6.2 GB | Fits | Get file → | |
| Q2_K | 5.3 GB | 6.2 GB | Fits | Get file → | |
| Q2_K_S | 5.3 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 5.4 GB | 6.3 GB | Fits | Get file → | |
| IQ4_NL | 5.4 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 5.4 GB | 6.3 GB | Fits | Get file → | |
| IQ3_M | 5.4 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_M | 5.7 GB | 6.6 GB | Fits | Get file → | |
| Q3_K_L | 5.8 GB | 6.8 GB | Fits | Get file → | |
| Q4_1 | 5.9 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_S | 6.4 GB | 7.3 GB | Tight | Get file → | |
| Q4_K_M | 6.8 GB | 7.7 GB | Tight | Get file → | |
| Q5_K_S | 6.9 GB | 7.8 GB | Tight | Get file → | |
| Q5_K_M | 7.3 GB | 8.2 GB | Too big | Get file → | |
| Q6_K | 9.5 GB | 10.4 GB | Too big | Get file → |
For 8 GB VRAM, use the IQ1_M quant (5.28 GB file, 6.2 GB memory at 8k context). If you have 12 GB VRAM, the Q4_K_S quant (6.39 GB file, 7.3 GB memory) offers a good balance of size and quality. For larger GPUs, the Q5_K_M quant (7.29 GB file, 8.2 GB memory) provides higher fidelity.
What GPU do you need for Gpt Oss Nano?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_S (6.9 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.5 GB file, about 10.4 GB in use).
Which Gpt Oss Nano quant should you choose?
Q4_K_M is the usual starting point for Gpt Oss Nano: it balances file size and quality well. Here it is a 6.8 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gpt Oss Nano
How much VRAM does Gpt Oss Nano need?
About 7.7 GB at Q4_K_M with an 8K context window. That is the 6.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Gpt Oss Nano on an 8 GB GPU?
Yes, with Q5_K_S: the 6.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gpt Oss Nano GGUF?
It depends on the quant: file is 0.0 GB, IQ1_M is 5.3 GB, IQ1_S is 5.3 GB, IQ2_XXS is 5.3 GB, IQ2_XS is 5.3 GB, Q3_K_S is 5.3 GB and 19 more.
What context length does Gpt Oss Nano support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Gpt Oss Nano GGUF?
The files are on Hugging Face in the mradermacher/gpt-oss-nano-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Gpt Oss Nano use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run GPT‑OSS‑Nano on 8 GB VRAM?
Yes, the IQ1_M quant uses 6.2 GB memory at 8k context, which fits within 8 GB VRAM.
Does GPT‑OSS‑Nano support vision?
No, the model is purely text‑based and does not include vision capabilities.