TI

TinyLlama v1.1

TinyllamaGGUF by QuantFactoryUpdated 2024-08-05
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant0.4 GB
Quick answer

TinyLlama v1.1 needs about 1.4 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.4 GB (Q2_K) to 1.2 GB (Q8_0).

TinyLlama v1.1 – 1.1B parameter Llama architecture

TinyLlama v1.1 is a 1.1B parameter Llama model quantized for efficient inference. It supports 2048 token context and is released under apache-2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Low memory inference
  • Fast token generation
  • Compatible with llama.cpp

Limits

  • No vision support
  • Limited to 2048 token context
  • Requires 1.1B parameter model

Best for

  • Embedded devices
  • Edge inference
  • Rapid prototyping

Who it’s for. Developers needing a small Llama model for local deployment. Researchers looking for a lightweight baseline for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.0 GB
Fits Get file →
Q3_K_S0.5 GB 1.0 GB
Fits Get file →
Q3_K_M0.5 GB 1.1 GB
Fits Get file →
Q3_K_L0.6 GB 1.1 GB
Fits Get file →
Q4_00.6 GB 1.2 GB
Fits Get file →
Q4_K_S0.6 GB 1.2 GB
Fits Get file →
Q4_K_M0.7 GB 1.2 GB
Fits Get file →
Q4_10.7 GB 1.2 GB
Fits Get file →
Q5_00.8 GB 1.3 GB
Fits Get file →
Q5_K_S0.8 GB 1.3 GB
Fits Get file →
Q5_K_M0.8 GB 1.3 GB
Fits Get file →
Q5_10.8 GB 1.4 GB
Fits Get file →
Q6_K0.9 GB 1.4 GB
Fits Get file →
Q8_01.2 GB 1.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.67 GB file, ~1.4 GB RAM). For 4 GB VRAM, use Q3_K_S (0.5 GB file, ~1.2 GB RAM). For 2 GB VRAM, use Q2_K (0.43 GB file, ~1.1 GB RAM). Estimates are approximate.

What GPU do you need for TinyLlama v1.1?

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 v1.1 quant should you choose?

Q4_K_M is the usual starting point for TinyLlama v1.1: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 GB, about 1.8 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 0.4 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
Parameters1.1B
Layers22
Trained context2,048 tokens
KV cache (fp16)22 KB per token

Source

Quantized byQuantFactory
FamilyTinyllama
Licenseapache-2.0
Downloads (HF)870
Last updated2024-08-05

Frequently asked questions about TinyLlama v1.1

How much VRAM does TinyLlama v1.1 need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.7 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 v1.1 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 v1.1 GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.5 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.6 GB, Q4_0 is 0.6 GB, Q4_K_S is 0.6 GB and 8 more.

What context length does TinyLlama v1.1 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 v1.1 GGUF?

The files are on Hugging Face in the QuantFactory/TinyLlama_v1.1-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 TinyLlama v1.1 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 TinyLlama v1.1 on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S quantizations will fit within 8 GB VRAM with approximate 1.4 GB RAM usage.

Does TinyLlama v1.1 support vision tasks?

No, the model is purely language and does not include vision capabilities.

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →