EK

Ekbasis Skopos 27B

EkbasisGGUF by mradermacherUpdated 2026-10-17
Download on Hugging Face
Parameters27B
Context256K
Layers65
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Ekbasis Skopos 27B needs about 19.2 GB of memory at Q4_K_M (a 16.5 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 22.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Ekbasis Skopos 27B – a 27 billion‑parameter Qwen‑3.5 model for action‑prediction

Ekbasis Skopos 27B is a 27 billion‑parameter Qwen‑3.5 model trained to predict the outcome of actions such as shell commands, git operations, and Python code. It provides calibrated, typed answers in a single forward pass without generating text. The model is released under the Apache‑2.0 license.

Good at

  • Predicting action outcomes accurately
  • Providing calibrated, typed responses
  • Serving with vLLM and serve.py

Limits

  • No vision support – mmproj files may be available separately
  • Large memory requirement for higher‑quality quants
  • Requires a 262144‑token context window

Best for

  • Command‑line safety checks
  • Git workflow analysis
  • Python test trace prediction

Who it’s for. Developers and researchers needing precise action‑prediction without text generation. The model is suitable for safety‑critical tooling and automated analysis of code and command sequences.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.1 GB 9.8 GB
Too big Get file →
IQ1_M7.6 GB 10.3 GB
Too big Get file →
IQ2_XXS8.4 GB 11.1 GB
Too big Get file →
IQ2_XS9.1 GB 11.8 GB
Too big Get file →
IQ2_S9.4 GB 12.0 GB
Too big Get file →
IQ2_M10.0 GB 12.7 GB
Too big Get file →
Q2_K_S10.2 GB 12.9 GB
Too big Get file →
Q2_K10.7 GB 13.4 GB
Too big Get file →
IQ3_XXS11.2 GB 13.9 GB
Too big Get file →
IQ3_XS12.0 GB 14.6 GB
Too big Get file →
Q3_K_S12.1 GB 14.8 GB
Too big Get file →
IQ3_S12.4 GB 15.1 GB
Too big Get file →
IQ3_M12.6 GB 15.3 GB
Too big Get file →
Q3_K_M13.3 GB 16.0 GB
Too big Get file →
Q3_K_L14.3 GB 17.0 GB
Too big Get file →
IQ4_XS15.1 GB 17.8 GB
Too big Get file →
Q4_015.5 GB 18.2 GB
Too big Get file →
Q4_K_S15.6 GB 18.3 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q4_117.1 GB 19.8 GB
Too big Get file →
Q5_K_S18.7 GB 21.4 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.15 GB, 9.8 GB memory) or IQ1_M (7.63 GB, 10.3 GB memory). For 12 GB VRAM, IQ2_S (9.09 GB, 11.8 GB memory) or Q2_K (10.71 GB, 13.4 GB memory) are suitable. Higher‑quality quants such as Q4_K_M (16.55 GB, 19.2 GB memory) require 20 GB+ VRAM.

What GPU do you need for Ekbasis Skopos 27B?

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 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_S (9.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.1 GB file, about 24.8 GB in use).

Which Ekbasis Skopos 27B quant should you choose?

Q4_K_M is the usual starting point for Ekbasis Skopos 27B: it balances file size and quality well. Here it is a 16.5 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

Architectureqwen35
Parameters27B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized bymradermacher
FamilyEkbasis
Licenseapache-2.0
Downloads (HF)2,877
Last updated2026-10-17

Frequently asked questions about Ekbasis Skopos 27B

How much VRAM does Ekbasis Skopos 27B need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Ekbasis Skopos 27B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ekbasis Skopos 27B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.1 GB, IQ1_M is 7.6 GB, IQ2_XXS is 8.4 GB, IQ2_XS is 9.1 GB, IQ2_S is 9.4 GB and 18 more.

What context length does Ekbasis Skopos 27B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download Ekbasis Skopos 27B GGUF?

The files are on Hugging Face in the mradermacher/Ekbasis-Skopos-27B-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 Ekbasis Skopos 27B 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 Skopos 27B on 8 GB VRAM?

Use the IQ1_S or IQ1_M quant, which fit within 8 GB VRAM and use about 10 GB of RAM at 8 k context.

Does Skopos 27B support vision tasks?

No, it is a text‑only model; mmproj files for vision are not included in the GGUF package.

What context length does Skopos 27B support?

It was trained on 262144 tokens and can handle that full context length.

Other GGUFs of Ekbasis-Skopos-27B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ekbasis models

All Ekbasis →

Other medium models

All medium models →