TE

TeenyTinyLlama 460m Chat

TeenytinyllamaGGUF by afridevaUpdated 2024-05-12
Download on Hugging Face
Parameters468M
Context2K
Layers24
Architecturellama
Smallest quant0.2 GB
Quick answer

TeenyTinyLlama 460m Chat needs about 1.6 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.2 GB (Q2_K) to 0.9 GB.

TeenyTinyLlama 460m Chat – a small Portuguese LLM

TeenyTinyLlama 460m Chat is a 0.468 billion‑parameter model fine‑tuned on Instruct‑Aira v2.0. It is trained exclusively on Brazilian Portuguese text and is intended for research and experimentation. The model is not a product and should not be used for human‑facing applications.

Good at

  • Portuguese language research
  • Low‑resource language experiments
  • Fine‑tuning for niche tasks

Limits

  • No vision support
  • Not suitable for other languages
  • Not for production use

Best for

  • Academic studies on low‑resource LLMs
  • Prototype Portuguese chatbots
  • Fine‑tuning experiments

Who it’s for. Researchers and developers working on low‑resource language models, especially those focusing on Brazilian Portuguese. The model is open‑source under Apache 2.0 and can be further fine‑tuned for specialized applications.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 0.9 GB
Fits Get file →
Q3_K_M0.2 GB 0.9 GB
Fits Get file →
Q4_K_M0.3 GB 1.0 GB
Fits Get file →
Q5_K_M0.3 GB 1.0 GB
Fits Get file →
Q6_K0.4 GB 1.1 GB
Fits Get file →
Q8_00.5 GB 1.2 GB
Fits Get file →
—0.9 GB 1.6 GB
Fits Get file →

For 8 GB VRAM, use Q2_K (0.19 GB) or Q3_K_M (0.24 GB). If 12 GB VRAM is available, Q4_K_M (0.29 GB) or Q5_K_M (0.34 GB) are suitable. Larger VRAM allows Q6_K (0.39 GB) or Q8_0 (0.5 GB).

What GPU do you need for TeenyTinyLlama 460m Chat?

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 the main file (0.9 GB file, about 2.2 GB in use).

Which TeenyTinyLlama 460m Chat quant should you choose?

Q4_K_M is the usual starting point for TeenyTinyLlama 460m Chat: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.5 GB, about 1.7 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 0.2 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
Parameters468M
Layers24
Trained context2,048 tokens
KV cache (fp16)96 KB per token

Source

Quantized byafrideva
Licenseapache-2.0
Downloads (HF)924
Last updated2024-05-12

Frequently asked questions about TeenyTinyLlama 460m Chat

How much VRAM does TeenyTinyLlama 460m Chat need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.3 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 TeenyTinyLlama 460m Chat on an 8 GB GPU?

Yes, with the smaller files: the 0.9 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TeenyTinyLlama 460m Chat GGUF?

It depends on the quant: Q2_K is 0.2 GB, Q3_K_M is 0.2 GB, Q4_K_M is 0.3 GB, Q5_K_M is 0.3 GB, Q6_K is 0.4 GB, Q8_0 is 0.5 GB and 1 more.

What context length does TeenyTinyLlama 460m Chat support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.2 GB at 2K.

Where can I download TeenyTinyLlama 460m Chat GGUF?

The files are on Hugging Face in the afrideva/TeenyTinyLlama-460m-Chat-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 TeenyTinyLlama 460m Chat 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 this model on 8 GB VRAM?

Yes, the Q2_K and Q3_K_M quantizations fit within 8 GB VRAM, using approximately 1.5 GB of memory at 8k context.

Does this model support English?

No, it is trained only on Brazilian Portuguese and is not suitable for other languages.

Is this model safe for production use?

No, the model is intended for research and experimentation and is not recommended for human‑facing production deployments.

Other GGUFs of TeenyTinyLlama-460m-Chat

Similar models

Browse all →

More from afrideva

All by afrideva →

More Teenytinyllama models

All Teenytinyllama →

Other tiny models

All tiny models →