GP

GPT OS3 Beta 8B A3B

GptGGUF by mradermacherUpdated 2025-08-25
Download on Hugging Face
Parameters8.37B
Context128K
Layers24
Architecturegpt-oss
Smallest quant5.0 GB
Quick answer

GPT OS3 Beta 8B A3B needs about 7.3 GB of memory at Q4_K_M (a 6.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 5.0 GB (Q3_K_S) to 16.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

GPT OS3 Beta 8B A3B is a 8.37B-parameter Gpt model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 12 quant files, from 5.0 GB (Q3_K_S) to 16.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S5.0 GB 5.9 GB
Fits Get file →
Q2_K5.0 GB 5.9 GB
Fits Get file →
IQ4_XS5.1 GB 6.0 GB
Fits Get file →
Q3_K_M5.3 GB 6.2 GB
Fits Get file →
Q3_K_L5.5 GB 6.4 GB
Fits Get file →
Q4_K_S6.0 GB 6.9 GB
Fits Get file →
Q4_K_M6.4 GB 7.3 GB
Tight Get file →
Q5_K_S6.5 GB 7.4 GB
Tight Get file →
Q5_K_M6.8 GB 7.7 GB
Tight Get file →
Q6_K8.8 GB 9.7 GB
Too big Get file →
Q8_08.9 GB 9.8 GB
Too big Get file →
F1616.8 GB 17.7 GB
Too big Get file →

What GPU do you need for GPT OS3 Beta 8B A3B?

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: the best quant that fits is IQ4_XS (5.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.8 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 9.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 9.8 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.8 GB file, about 17.7 GB in use).

Which GPT OS3 Beta 8B A3B quant should you choose?

Q4_K_M is the usual starting point for GPT OS3 Beta 8B A3B: it balances file size and quality well. Here it is a 6.4 GB file.

The Q8_0 file is 8.9 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.

If memory is tight, the smallest file is Q3_K_S at 5.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters8.37B (approximate, mixture of experts)
Active parameters3B
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyGpt
Licenseapache-2.0
Downloads (HF)184
Last updated2025-08-25

Frequently asked questions about GPT OS3 Beta 8B A3B

How much VRAM does GPT OS3 Beta 8B A3B need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 6.4 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 OS3 Beta 8B A3B on an 8 GB GPU?

Yes, with Q5_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 OS3 Beta 8B A3B GGUF?

It depends on the quant: Q3_K_S is 5.0 GB, Q2_K is 5.0 GB, IQ4_XS is 5.1 GB, Q3_K_M is 5.3 GB, Q3_K_L is 5.5 GB, Q4_K_S is 6.0 GB and 6 more.

What context length does GPT OS3 Beta 8B A3B 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 OS3 Beta 8B A3B GGUF?

The files are on Hugging Face in the mradermacher/GPT-OS3-Beta-8B-A3B-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 OS3 Beta 8B A3B 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.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gpt models

All Gpt →

Other small models

All small models →