GP

gpt oss nano

gpt-ossGGUF by squ11z1Updated 2026-07-14
Download on Hugging Face
Parameters9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant6.8 GB
Quick answer

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 3 quants, from 6.8 GB (Q4_K_M) to 18.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Compact 9B GPT-OSS model optimized for step‑by‑step reasoning

GPT‑OSS‑Nano is a 9B parameter Mixture of Experts model built on the GPT‑OSS architecture. It is fine‑tuned for chain‑of‑thought reasoning and problem solving, using only ~3B active parameters per forward pass. The model supports a 128K context window and is released under Apache 2.0.

Good at

  • Step‑by‑step reasoning
  • Chain‑of‑thought problem solving
  • Sparse expert activation

Limits

  • Large context requires significant VRAM
  • No vision support
  • Limited multilingual performance

Best for

  • Local reasoning tasks
  • Fine‑tuning for specialized domains
  • Low‑latency inference on 16GB GPUs

Who it’s for. Developers needing a lightweight reasoning model for local deployment. Researchers can fine‑tune it for domain‑specific tasks. It is suitable for applications that require chain‑of‑thought explanations without heavy hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M6.8 GB 7.7 GB
Tight Get file →
Q8_09.5 GB 10.5 GB
Too big Get file →
BF1618.0 GB 18.9 GB
Too big Get file →

For 8GB VRAM, use Q4_K_M (6.83 GB file, ~7.7 GB memory at 8K context). For 16GB VRAM, Q8_0 (9.55 GB file, ~10.5 GB memory) is safe. BF16 requires ~18.9 GB memory and is best on larger GPUs.

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q4_K_M (6.8 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 10.5 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (18.0 GB file, about 18.9 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.

The Q8_0 file is 9.5 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized bysqu11z1
Familygpt-oss
Licenseapache-2.0
Downloads (HF)2,573
Last updated2026-07-14

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 Q4_K_M: the 6.8 GB file needs about 7.7 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: Q4_K_M is 6.8 GB, Q8_0 is 9.5 GB, BF16 is 18.0 GB.

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 squ11z1/gpt-oss-nano 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 8GB VRAM?

Yes, using the Q4_K_M quantization which requires about 7.7 GB of VRAM at 8K context.

Does this model support vision tasks?

No, GPT‑OSS‑Nano is a text‑only model and does not include vision capabilities.

Other GGUFs of gpt-oss-20b

Similar models

Browse all →

More from squ11z1

All by squ11z1 →

More gpt-oss models

All gpt-oss →

Other small models

All small models →