TI

TinyLlama 3T Cinder v1.2

TinyllamaGGUF by JosephgflowersUpdated 2025-01-06
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant1.2 GB
Quick answer

TinyLlama 3T Cinder v1.2 needs about 1.9 GB of memory at Q8_0 (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.2 GB (Q8_0) to 1.2 GB (Q8_0).

TinyLlama 3T Cinder v1.2 – 1.1B parameter chatbot for science and education

TinyLlama 3T Cinder v1.2 is a 1.1B parameter model built on the TinyLlama architecture. It is trained on a mix of interactive GPT‑4 chats, Open Orca, OpenAssistant, and other educational datasets. The model focuses on scientific and STEM conversations.

Good at

  • STEM Q&A
  • Educational dialogue
  • Scientific storytelling

Limits

  • No vision support
  • Limited context to 2048 tokens
  • MIT license only

Best for

  • Chatbot for science tutoring
  • Interactive STEM workshops
  • Educational content generation

Who it’s for. Developers and educators looking for a lightweight, science‑focused chatbot. The model is suitable for applications that require quick, context‑limited responses in educational settings.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.2 GB 1.7 GB
Fits Get file →
Q8_01.2 GB 1.7 GB
Fits Get file →

For 8 GB VRAM, use the Q8_0 quantization; the file is 1.17 GB and requires about 1.9 GB of VRAM at 8 k context. For 4 GB VRAM, the same quant is still the only available option, but memory usage will be close to the limit. Larger VRAM allows the same file to run comfortably.

What GPU do you need for TinyLlama 3T Cinder v1.2?

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 Q8_0 (1.2 GB file, about 1.9 GB in use).

Which TinyLlama 3T Cinder v1.2 quant should you choose?

Q8_0 (1.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.1B
Layers22
Trained context2,048 tokens
KV cache (fp16)22 KB per token

Source

Quantized byJosephgflowers
FamilyTinyllama
Licensemit
Downloads (HF)793
Last updated2025-01-06

Frequently asked questions about TinyLlama 3T Cinder v1.2

How much VRAM does TinyLlama 3T Cinder v1.2 need?

About 1.9 GB at Q8_0 with an 8K context window. That is the 1.2 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 TinyLlama 3T Cinder v1.2 on an 8 GB GPU?

Yes, with Q8_0: the 1.2 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyLlama 3T Cinder v1.2 GGUF?

It depends on the quant: Q8_0 is 1.2 GB, Q8_0 is 1.2 GB.

What context length does TinyLlama 3T Cinder v1.2 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.

Where can I download TinyLlama 3T Cinder v1.2 GGUF?

The files are on Hugging Face in the Josephgflowers/TinyLlama-3T-Cinder-v1.2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does TinyLlama 3T Cinder v1.2 use?

Hugging Face lists the license as mit. 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 TinyLlama 3T Cinder v1.2 on 8 GB VRAM?

Yes, the Q8_0 file is 1.17 GB and requires about 1.9 GB of VRAM at 8 k context, which fits within 8 GB.

Does this model support vision or image input?

No, the model does not include vision capabilities.

What is the context length of this model?

The trained context length is 2048 tokens.

Similar models

Browse all →

More from Josephgflowers

All by Josephgflowers →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →