TI

qw us tinyllama 1b

TinyllamaGGUF by paul-stansiferUpdated 2024-09-23
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant1.2 GB
Quick answer

qw us tinyllama 1b 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 2.2 GB (F16).

qw us tinyllama 1b – a compact 1.1B‑parameter Llama model

qw us tinyllama 1b is a 1.1B‑parameter Llama model derived from TinyLlama/TinyLlama_v1.1. It is trained on 2 trillion tokens and fine‑tuned with Unsloth and TRL. The model is available in Q8_0 and F16 quantizations.

Good at

  • Fast inference on modest hardware
  • Low memory footprint
  • Compatible with llama.cpp

Limits

  • No vision support
  • Context limited to 2048 tokens
  • Apache‑2.0 license

Best for

  • Local chatbot deployments
  • Edge inference
  • Rapid prototyping

Who it’s for. Developers needing a lightweight Llama model for local inference. The model is suitable for projects that require quick setup and low resource consumption.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.2 GB 1.7 GB
Fits Get file →
F162.2 GB 2.7 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (1.17 GB file, ~1.9 GB memory at 8k context). If more memory is available, F16 (2.2 GB file, ~2.9 GB memory) offers higher precision.

What GPU do you need for qw us tinyllama 1b?

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 F16 (2.2 GB file, about 2.9 GB in use).

Which qw us tinyllama 1b 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 bypaul-stansifer
FamilyTinyllama
Licenseapache-2.0
Downloads (HF)559
Last updated2024-09-23

Frequently asked questions about qw us tinyllama 1b

How much VRAM does qw us tinyllama 1b 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 qw us tinyllama 1b on an 8 GB GPU?

Yes, with F16: the 2.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of qw us tinyllama 1b GGUF?

It depends on the quant: Q8_0 is 1.2 GB, F16 is 2.2 GB.

What context length does qw us tinyllama 1b 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 qw us tinyllama 1b GGUF?

The files are on Hugging Face in the paul-stansifer/qw-us-tinyllama-1b-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 qw us tinyllama 1b 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 qw us tinyllama 1b on 8 GB VRAM?

Yes, the Q8_0 quantization requires about 1.9 GB of VRAM at 8k context, which fits within 8 GB.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of TinyLlama_v1.1

Similar models

Browse all →

More from paul-stansifer

All by paul-stansifer →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →