SO

Sophea OSS v1

SopheaGGUF by mradermacherUpdated 2026-09-16
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant0.0 GB
Quick answer

Sophea OSS v1 needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Sophea OSS v1 – 20.9B Greek/English reasoning LLM

Sophea OSS v1 is a 20.9B parameter GPT‑OSS model fine‑tuned for Greek and English reasoning. It uses a sparse MoE transformer with 4‑of‑32 routing and includes a dedicated analysis channel for reasoning traces.

Good at

  • Greek and English reasoning
  • analysis channel tracing
  • consistent language handling

Limits

  • Answer‑channel leak 10.3%
  • Not evaluated for safety‑critical use
  • No vision support

Best for

  • Deployments needing Greek/English reasoning
  • Applications that read analysis traces
  • Environments with 8‑k context

Who it’s for. Developers building reasoning assistants for Greek and English. Researchers interested in sparse MoE models and trace‑based reasoning. Teams that can handle a higher answer‑channel leak and do not require safety‑critical validation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_M12.0 GB 12.9 GB
Too big Get file →
IQ1_S12.0 GB 12.9 GB
Too big Get file →
IQ2_XXS12.0 GB 12.9 GB
Too big Get file →
IQ2_XS12.0 GB 12.9 GB
Too big Get file →
Q3_K_S12.1 GB 13.0 GB
Too big Get file →
IQ2_M12.1 GB 13.0 GB
Too big Get file →
IQ2_S12.1 GB 13.0 GB
Too big Get file →
IQ3_S12.1 GB 13.0 GB
Too big Get file →
IQ3_XS12.1 GB 13.0 GB
Too big Get file →
IQ3_XXS12.1 GB 13.0 GB
Too big Get file →
Q2_K12.1 GB 13.0 GB
Too big Get file →
IQ4_XS12.1 GB 13.0 GB
Too big Get file →
Q2_K_S12.1 GB 13.0 GB
Too big Get file →
Q4_012.1 GB 13.1 GB
Too big Get file →
IQ3_M12.2 GB 13.1 GB
Too big Get file →
Q3_K_M12.9 GB 13.8 GB
Too big Get file →
Q3_K_L13.3 GB 14.2 GB
Too big Get file →
Q4_113.4 GB 14.3 GB
Too big Get file →
Q4_K_S14.7 GB 15.6 GB
Too big Get file →
Q4_K_M15.8 GB 16.7 GB
Too big Get file →
Q5_K_S15.9 GB 16.8 GB
Too big Get file →
Q5_K_M16.9 GB 17.8 GB
Too big Get file →
Q6_K22.2 GB 23.1 GB
Too big Get file →

For 8‑GB VRAM use IQ1_M or IQ1_S (12.02 GB file, ~12.9 GB RAM). For 12‑GB VRAM use Q3_K_S or IQ2_M (12.06–12.07 GB file, ~13 GB RAM). For 16‑GB VRAM use Q4_K_M (15.81 GB file, ~16.7 GB RAM).

What GPU do you need for Sophea OSS v1?

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 the main file (0.0 GB file, about 0.9 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 23.1 GB in use).

Which Sophea OSS v1 quant should you choose?

Q4_K_M is the usual starting point for Sophea OSS v1: it balances file size and quality well. Here it is a 15.8 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

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilySophea
Licenseapache-2.0
Downloads (HF)466
Last updated2026-09-16

Frequently asked questions about Sophea OSS v1

How much VRAM does Sophea OSS v1 need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 Sophea OSS v1 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sophea OSS v1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_M is 12.0 GB, IQ1_S is 12.0 GB, IQ2_XXS is 12.0 GB, IQ2_XS is 12.0 GB, Q3_K_S is 12.1 GB and 18 more.

What context length does Sophea OSS v1 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 Sophea OSS v1 GGUF?

The files are on Hugging Face in the mradermacher/Sophea-OSS-v1-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 Sophea OSS v1 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 Sophea OSS v1 on 8 GB VRAM?

Use the IQ1_M or IQ1_S quant, which are 12.02 GB files and require about 12.9 GB of RAM at 8‑k context.

What is the answer‑channel leak?

The model leaks 10.3% of the answer channel, meaning some answer content may appear in the reasoning trace.

Is this model safe for medical use?

It has not been evaluated for safety‑critical, legal, or medical use.

Other GGUFs of Sophea-OSS-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sophea models

All Sophea →

Other medium models

All medium models →