BL

Q3.5 BlueStar 27B ultra heretic

BluestarGGUF by CountCandyUpdated 2026-03-05
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant28.6 GB
Quick answer

Q3.5 BlueStar 27B ultra heretic needs about 31.2 GB of memory at Q8_0 (a 28.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 28.6 GB (Q8_0) to 53.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Q3.5 BlueStar 27B ultra heretic is a 26.9B-parameter Bluestar model in GGUF format, quantized by CountCandy. Its trained context length is 256K tokens. The repository has 2 quant files, from 28.6 GB (Q8_0) to 53.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_028.6 GB 31.2 GB
Too big Get file →
F1653.8 GB 56.5 GB
Too big Get file →

What GPU do you need for Q3.5 BlueStar 27B ultra heretic?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which Q3.5 BlueStar 27B ultra heretic quant should you choose?

Q8_0 (28.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byCountCandy
FamilyBluestar
Licensemit
Downloads (HF)29
Last updated2026-03-05

Frequently asked questions about Q3.5 BlueStar 27B ultra heretic

How much VRAM does Q3.5 BlueStar 27B ultra heretic need?

About 31.2 GB at Q8_0 with an 8K context window. That is the 28.6 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 Q3.5 BlueStar 27B ultra heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Q3.5 BlueStar 27B ultra heretic GGUF?

It depends on the quant: Q8_0 is 28.6 GB, F16 is 53.8 GB.

What context length does Q3.5 BlueStar 27B ultra heretic support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Q3.5 BlueStar 27B ultra heretic GGUF?

The files are on Hugging Face in the CountCandy/Q3.5-BlueStar-27B-ultra-heretic-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 Q3.5 BlueStar 27B ultra heretic use?

Hugging Face lists the license as mit. 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 Q3.5-BlueStar-27B-ultra-heretic

Similar models

Browse all →

More from CountCandy

All by CountCandy →

More Bluestar models

All Bluestar →

Other medium models

All medium models →