QW

Satella RAG 27B

QwenGGUF by EphAsadUpdated 2026-10-20
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant19.5 GB
Quick answer

Satella RAG 27B needs about 25.1 GB of memory at Q6_K (a 22.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 19.5 GB (Q5_K_M) to 29.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Satella RAG 27B is a 27.3B-parameter Qwen model in GGUF format, quantized by EphAsad. Its trained context length is 256K tokens. The repository has 3 quant files, from 19.5 GB (Q5_K_M) to 29.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M19.5 GB 22.2 GB
Too big Get file →
Q6_K22.4 GB 25.1 GB
Too big Get file →
Q8_029.0 GB 31.7 GB
Too big Get file →

What GPU do you need for Satella RAG 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).

Which Satella RAG 27B quant should you choose?

Q6_K (22.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K_M at 19.5 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters27.3B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized byEphAsad
FamilyQwen
Licenseapache-2.0
Downloads (HF)264
Last updated2026-10-20

Frequently asked questions about Satella RAG 27B

How much VRAM does Satella RAG 27B need?

About 25.1 GB at Q6_K with an 8K context window. That is the 22.4 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 Satella RAG 27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Satella RAG 27B GGUF?

It depends on the quant: Q5_K_M is 19.5 GB, Q6_K is 22.4 GB, Q8_0 is 29.0 GB.

What context length does Satella RAG 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 Satella RAG 27B GGUF?

The files are on Hugging Face in the EphAsad/Satella-RAG-27B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Satella RAG 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.

Other GGUFs of Qwen3.5-27B

Similar models

Browse all →

More from EphAsad

All by EphAsad →

More Qwen models

All Qwen →

Other medium models

All medium models →