PR

Priya 3B

PriyaGGUF by mradermacherUpdated 2024-12-06
Download on Hugging Face
Parameters2.81B
Context128K
Layers24
Architecturellama
Smallest quant0.8 GB
Quick answer

Priya 3B needs about 3.1 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.8 GB (IQ1_S) to 2.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Priya 3B – a 3B‑parameter teen‑centric LLM

Priya 3B is a 2.81B parameter model built on the llama architecture. It was trained on teen conversations, tech discussions, and memes to deliver a sweet and savage personality. The model supports a 131072 token context window.

Good at

  • Teen‑style dialogue
  • Tech and meme references
  • Short‑form conversational tasks

Limits

  • No vision support
  • May hallucinate on complex queries
  • License is other – check terms

Best for

  • Chatbots for casual users
  • Personal assistants with a playful tone
  • Short content generation

Who it’s for. Developers looking for a lightweight, personality‑driven model for local deployment. Ideal for hobbyists and small‑scale applications that need a conversational agent with a teen vibe.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.8 GB 2.1 GB
Fits Get file →
IQ1_M0.8 GB 2.1 GB
Fits Get file →
IQ2_XXS0.9 GB 2.2 GB
Fits Get file →
IQ2_XS1.0 GB 2.3 GB
Fits Get file →
IQ2_S1.0 GB 2.3 GB
Fits Get file →
IQ2_M1.1 GB 2.4 GB
Fits Get file →
Q2_K_S1.1 GB 2.4 GB
Fits Get file →
IQ3_XXS1.2 GB 2.5 GB
Fits Get file →
Q2_K1.2 GB 2.5 GB
Fits Get file →
IQ3_XS1.3 GB 2.6 GB
Fits Get file →
IQ3_S1.4 GB 2.7 GB
Fits Get file →
Q3_K_S1.4 GB 2.7 GB
Fits Get file →
IQ3_M1.4 GB 2.7 GB
Fits Get file →
Q3_K_M1.5 GB 2.8 GB
Fits Get file →
Q3_K_L1.6 GB 2.9 GB
Fits Get file →
IQ4_XS1.6 GB 2.9 GB
Fits Get file →
Q4_01.7 GB 3.0 GB
Fits Get file →
Q4_01.7 GB 3.0 GB
Fits Get file →
Q4_01.7 GB 3.0 GB
Fits Get file →
Q4_01.7 GB 3.0 GB
Fits Get file →
Q4_K_S1.7 GB 3.0 GB
Fits Get file →
Q4_K_M1.8 GB 3.1 GB
Fits Get file →
Q5_K_S2.0 GB 3.3 GB
Fits Get file →
Q5_K_M2.0 GB 3.3 GB
Fits Get file →
Q6_K2.3 GB 3.6 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (0.79 GB) or IQ1_M (0.83 GB). If 12 GB VRAM is available, IQ2_S (1.03 GB) or Q2_K_S (1.37 GB) provide a good balance of size and performance. For 16 GB VRAM, Q4_K_M (1.78 GB) or Q5_K_S (1.99 GB) are suitable options.

What GPU do you need for Priya 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 Q6_K (2.3 GB file, about 3.6 GB in use).

Which Priya 3B quant should you choose?

Q4_K_M is the usual starting point for Priya 3B: it balances file size and quality well. Here it is a 1.8 GB file.

If memory is tight, the smallest file is IQ1_S at 0.8 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
Parameters2.81B
Layers24
Trained context131,072 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyPriya
Licenseother
Downloads (HF)688
Last updated2024-12-06

Frequently asked questions about Priya 3B

How much VRAM does Priya 3B need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.8 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 Priya 3B on an 8 GB GPU?

Yes, with Q6_K: the 2.3 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Priya 3B GGUF?

It depends on the quant: IQ1_S is 0.8 GB, IQ1_M is 0.8 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.0 GB, IQ2_M is 1.1 GB and 19 more.

What context length does Priya 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 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Priya 3B GGUF?

The files are on Hugging Face in the mradermacher/Priya-3B-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 Priya 3B use?

Hugging Face lists the license as other. 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 Priya 3B on 8 GB VRAM?

Yes, the smallest quant IQ1_S uses 0.79 GB file size and estimates 2.1 GB VRAM at 8 k context.

Does Priya 3B support image input?

No, the model has no vision capabilities.

Other GGUFs of Priya-3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Priya models

All Priya →

Other tiny models

All tiny models →