TI

TinyLlama-1.1B-step-50K-105b

TinyllamaGGUF by RichardErkhovUpdated 2024-06-22
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant0.4 GB
Quick answer

TinyLlama-1.1B-step-50K-105b 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 22 quants, from 0.4 GB (Q2_K) to 1.2 GB (Q8_0).

TinyLlama‑1.1B‑step‑50K‑105b – a compact 1.1B‑parameter Llama model

TinyLlama‑1.1B‑step‑50K‑105b is a 1.1B‑parameter Llama architecture model trained on 3 trillion tokens. It supports a 2048‑token context window and is available in multiple GGUF quantizations.

Good at

  • Fast inference on low‑memory GPUs
  • Small footprint for edge deployment
  • Compatible with llama.cpp

Limits

  • No vision support
  • License not specified
  • Requires at least 1.1 GB VRAM for Q2_K

Best for

  • Local chatbot applications
  • Rapid prototyping
  • Embedded inference

Who it’s for. Developers needing a lightweight Llama model for local inference. Suitable for projects with limited GPU memory or for quick experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.0 GB
Fits Get file →
IQ3_XS0.5 GB 1.0 GB
Fits Get file →
Q3_K_S0.5 GB 1.0 GB
Fits Get file →
IQ3_S0.5 GB 1.0 GB
Fits Get file →
IQ3_M0.5 GB 1.1 GB
Fits Get file →
Q3_K0.5 GB 1.1 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 →
IQ4_XS0.6 GB 1.2 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 →
IQ4_NL0.6 GB 1.2 GB
Fits Get file →
Q4_K0.7 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_K0.8 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, Q4_K_M (0.67 GB, 1.4 GB memory) or Q5_K_M (0.78 GB, 1.5 GB memory) are suitable. For 4 GB VRAM, Q2_K (0.43 GB, 1.1 GB memory) or IQ3_XS (0.48 GB, 1.2 GB memory) are recommended. Larger quants require more VRAM.

What GPU do you need for TinyLlama-1.1B-step-50K-105b?

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-1.1B-step-50K-105b quant should you choose?

Q4_K_M is the usual starting point for TinyLlama-1.1B-step-50K-105b: 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 byRichardErkhov
FamilyTinyllama
Downloads (HF)661
Last updated2024-06-22

Frequently asked questions about TinyLlama-1.1B-step-50K-105b

How much VRAM does TinyLlama-1.1B-step-50K-105b 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-1.1B-step-50K-105b 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-1.1B-step-50K-105b GGUF?

It depends on the quant: Q2_K is 0.4 GB, IQ3_XS is 0.5 GB, Q3_K_S is 0.5 GB, IQ3_S is 0.5 GB, IQ3_M is 0.5 GB, Q3_K is 0.5 GB and 16 more.

What context length does TinyLlama-1.1B-step-50K-105b 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-1.1B-step-50K-105b GGUF?

The files are on Hugging Face in the RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run TinyLlama‑1.1B‑step‑50K‑105b on 8 GB VRAM?

Yes, Q4_K_M or Q5_K_M quantizations fit within 8 GB VRAM, using approximately 1.4–1.5 GB of memory at 8K context.

What is the context length of this model?

The model supports a 2048‑token context window.

Does this model support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →