BL

.\BlackSheep MoE

BlacksheepGGUF by mradermacherUpdated 2025-03-11
Download on Hugging Face
Parameters11.1B
Context16K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

.\BlackSheep MoE needs about 10.4 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 17 quants, from 4.1 GB (Q2_K) to 9.1 GB (Q6_K).

.\BlackSheep MoE is a 11.1B-parameter Blacksheep model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 17 quant files, from 4.1 GB (Q2_K) to 9.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.1 GB 7.8 GB
Tight Get file →
IQ3_XXS4.3 GB 8.0 GB
Tight Get file →
IQ3_XS4.5 GB 8.3 GB
Too big Get file →
IQ3_S4.8 GB 8.5 GB
Too big Get file →
Q3_K_S4.8 GB 8.5 GB
Too big Get file →
IQ3_M4.9 GB 8.7 GB
Too big Get file →
Q3_K_M5.3 GB 9.1 GB
Too big Get file →
Q3_K_L5.8 GB 9.5 GB
Too big Get file →
IQ4_XS5.9 GB 9.6 GB
Too big Get file →
IQ4_NL6.3 GB 10.0 GB
Too big Get file →
Q4_06.3 GB 10.0 GB
Too big Get file →
Q4_K_S6.3 GB 10.0 GB
Too big Get file →
Q4_K_M6.7 GB 10.4 GB
Too big Get file →
Q4_16.9 GB 10.7 GB
Too big Get file →
Q5_K_S7.6 GB 11.3 GB
Too big Get file →
Q5_K_M7.9 GB 11.6 GB
Too big Get file →
Q6_K9.1 GB 12.8 GB
Too big Get file →

What GPU do you need for .\BlackSheep MoE?

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: the best quant that fits is IQ3_XXS (4.3 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (7.9 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (9.1 GB file, about 12.8 GB in use).

Which .\BlackSheep MoE quant should you choose?

Q4_K_M is the usual starting point for .\BlackSheep MoE: it balances file size and quality well. Here it is a 6.7 GB file.

If memory is tight, the smallest file is Q2_K at 4.1 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
Parameters11.1B (approximate, mixture of experts)
Layers32
Trained context16,384 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
Downloads (HF)35
Last updated2025-03-11

Frequently asked questions about .\BlackSheep MoE

How much VRAM does .\BlackSheep MoE need?

About 10.4 GB at Q4_K_M with an 8K context window. That is the 6.7 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 MoE on an 8 GB GPU?

Yes, with IQ3_XXS: the 4.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of .\BlackSheep MoE GGUF?

It depends on the quant: Q2_K is 4.1 GB, IQ3_XXS is 4.3 GB, IQ3_XS is 4.5 GB, IQ3_S is 4.8 GB, Q3_K_S is 4.8 GB, IQ3_M is 4.9 GB and 11 more.

What context length does .\BlackSheep MoE support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 3.2 GB at 8K and 6.4 GB at 16K.

Where can I download .\BlackSheep MoE GGUF?

The files are on Hugging Face in the mradermacher/BlackSheep-MoE-4x3B-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 .\BlackSheep MoE use?

Hugging Face lists the license as cc-by-sa-4.0. 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 BlackSheep-MoE-4x3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Blacksheep models

All Blacksheep →

Other medium models

All medium models →