BL

BlackSheep Large

BlacksheepGGUF by mradermacherUpdated 2026-10-11
Download on Hugging Face
Parameters27.7B
Context128K
Layers70
Architecturellama
Smallest quant10.3 GB
Quick answer

BlackSheep Large needs about 19.4 GB of memory at Q4_K_M (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.3 GB (Q2_K) to 29.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.

BlackSheep Large is a 27.7B-parameter Blacksheep model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 11 quant files, from 10.3 GB (Q2_K) to 29.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.3 GB 13.1 GB
Too big Get file →
Q3_K_S12.0 GB 14.8 GB
Too big Get file →
Q3_K_M13.4 GB 16.2 GB
Too big Get file →
Q3_K_L14.6 GB 17.4 GB
Too big Get file →
IQ4_XS15.0 GB 17.8 GB
Too big Get file →
Q4_K_S15.7 GB 18.6 GB
Too big Get file →
Q4_K_M16.6 GB 19.4 GB
Too big Get file →
Q5_K_S19.1 GB 21.9 GB
Too big Get file →
Q5_K_M19.6 GB 22.4 GB
Too big Get file →
Q6_K22.7 GB 25.6 GB
Too big Get file →
Q8_029.4 GB 32.3 GB
Too big Get file →

What GPU do you need for BlackSheep Large?

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: the best quant that fits is Q3_K_S (12.0 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.6 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.7 GB file, about 25.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (29.4 GB file, about 32.3 GB in use).

Which BlackSheep Large quant should you choose?

Q4_K_M is the usual starting point for BlackSheep Large: it balances file size and quality well. Here it is a 16.6 GB file.

The Q8_0 file is 29.4 GB, about 1.8 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 Q2_K at 10.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters27.7B
Layers70
Trained context131,072 tokens
KV cache (fp16)280 KB per token

Source

Quantized bymradermacher
Downloads (HF)189
Last updated2026-10-11

Frequently asked questions about BlackSheep Large

How much VRAM does BlackSheep Large need?

About 19.4 GB at Q4_K_M with an 8K context window. That is the 16.6 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 BlackSheep Large on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BlackSheep Large GGUF?

It depends on the quant: Q2_K is 10.3 GB, Q3_K_S is 12.0 GB, Q3_K_M is 13.4 GB, Q3_K_L is 14.6 GB, IQ4_XS is 15.0 GB, Q4_K_S is 15.7 GB and 5 more.

What context length does BlackSheep Large support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.4 GB at 32K.

Where can I download BlackSheep Large GGUF?

The files are on Hugging Face in the mradermacher/BlackSheep-Large-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 BlackSheep Large use?

Hugging Face lists the license as artistic-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 Blacksheep models

All Blacksheep →

Other medium models

All medium models →