LL

BlackSheep Llama3.2 3B

LlamaGGUF by mradermacherUpdated 2025-03-29
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant0.9 GB
Quick answer

BlackSheep Llama3.2 3B needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.9 GB (IQ1_S) to 2.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

BlackSheep Llama3.2 3B – a 3.21B parameter model focused on context obedience

BlackSheep Llama3.2 3B is a 3.21B parameter Llama model fine‑tuned for enhanced adherence to provided context and reduced hallucinations. It uses explicit delimiters to improve RAG performance. The model is released under the apache-2.0 license.

Good at

  • Context‑obeying responses
  • RAG with source citation
  • Tool‑use prompts

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache-2.0

Best for

  • RAG applications
  • Chatbots needing source references
  • Tool‑enabled workflows

Who it’s for. Developers building retrieval‑augmented chat systems or tool‑using agents who need reliable context adherence. The model is suitable for users with access to GGUF-compatible runtimes such as llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.9 GB 2.3 GB
Fits Get file →
IQ1_M0.9 GB 2.4 GB
Fits Get file →
IQ2_XXS1.0 GB 2.5 GB
Fits Get file →
IQ2_XS1.1 GB 2.5 GB
Fits Get file →
IQ2_S1.2 GB 2.6 GB
Fits Get file →
IQ2_M1.2 GB 2.7 GB
Fits Get file →
IQ3_XXS1.3 GB 2.8 GB
Fits Get file →
Q2_K1.4 GB 2.8 GB
Fits Get file →
IQ3_XS1.5 GB 2.9 GB
Fits Get file →
IQ3_S1.5 GB 3.0 GB
Fits Get file →
Q3_K_S1.5 GB 3.0 GB
Fits Get file →
IQ3_M1.6 GB 3.0 GB
Fits Get file →
Q3_K_M1.7 GB 3.1 GB
Fits Get file →
Q3_K_L1.8 GB 3.3 GB
Fits Get file →
IQ4_XS1.8 GB 3.3 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_K_S1.9 GB 3.4 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q5_K_S2.3 GB 3.7 GB
Fits Get file →
Q5_K_M2.3 GB 3.8 GB
Fits Get file →
Q6_K2.6 GB 4.1 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (0.87 GB) or IQ1_M (0.92 GB). If 12 GB VRAM is available, Q4_K_M (2.02 GB) or Q5_K_M (2.32 GB) provide a good balance of size and performance. Larger quants such as Q6_K (2.64 GB) require more memory but offer higher precision.

What GPU do you need for BlackSheep Llama3.2 3B?

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 Q5_K_M (2.3 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (2.6 GB file, about 4.1 GB in use).

Which BlackSheep Llama3.2 3B quant should you choose?

Q4_K_M is the usual starting point for BlackSheep Llama3.2 3B: it balances file size and quality well. Here it is a 2.0 GB file.

If memory is tight, the smallest file is IQ1_S at 0.9 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
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Frequently asked questions about BlackSheep Llama3.2 3B

How much VRAM does BlackSheep Llama3.2 3B need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Llama3.2 3B on an 8 GB GPU?

Yes, with Q6_K: the 2.6 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of BlackSheep Llama3.2 3B GGUF?

It depends on the quant: IQ1_S is 0.9 GB, IQ1_M is 0.9 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.1 GB, IQ2_S is 1.2 GB, IQ2_M is 1.2 GB and 18 more.

What context length does BlackSheep Llama3.2 3B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download BlackSheep Llama3.2 3B GGUF?

The files are on Hugging Face in the mradermacher/BlackSheep-Llama3.2-3B-Context_Obedient-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 Llama3.2 3B 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 BlackSheep Llama3.2 3B on 8 GB VRAM?

Yes, the IQ1_S and IQ1_M quants are under 1 GB and require about 2.3–2.4 GB of VRAM at 8k context.

Does the model support vision?

No, the model has no vision capability.

What license does the model use?

The model is released under the apache-2.0 license.

Other GGUFs of BlackSheep-Llama3.2-3B-Context_Obedient

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other tiny models

All tiny models →