LL

Lekhansh Llama 3.2 1B Base Model cpt merged

LlamaGGUF by RichardErkhovUpdated 2024-10-29
Download on Hugging Face
Parameters1.5B
Context128K
Layers—
Architecturellama
Smallest quant0.5 GB
Quick answer

Lekhansh Llama 3.2 1B Base Model cpt merged needs about 1.1 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.5 GB (Q4_K_M) to 1.6 GB (Q8_0).

Lekhansh Llama 3.2 1B Base Model cpt merged is a 1.5B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 19 quant files, from 0.5 GB (Q4_K_M) to 1.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.1 GB
Fits Get file →
Q2_K0.7 GB 1.2 GB
Fits Get file →
Q3_K0.7 GB 1.3 GB
Fits Get file →
Q3_K_S0.8 GB 1.3 GB
Fits Get file →
Q3_K_M0.8 GB 1.4 GB
Fits Get file →
Q3_K_L0.8 GB 1.4 GB
Fits Get file →
IQ4_XS0.9 GB 1.5 GB
Fits Get file →
Q4_00.9 GB 1.5 GB
Fits Get file →
Q4_K_S0.9 GB 1.5 GB
Fits Get file →
IQ4_NL0.9 GB 1.5 GB
Fits Get file →
Q4_K1.0 GB 1.6 GB
Fits Get file →
Q4_11.0 GB 1.6 GB
Fits Get file →
Q5_01.1 GB 1.7 GB
Fits Get file →
Q5_K_S1.1 GB 1.7 GB
Fits Get file →
Q5_K1.1 GB 1.7 GB
Fits Get file →
Q5_K_M1.1 GB 1.7 GB
Fits Get file →
Q5_11.2 GB 1.8 GB
Fits Get file →
Q6_K1.2 GB 1.9 GB
Fits Get file →
Q8_01.6 GB 2.3 GB
Fits Get file →

What GPU do you need for Lekhansh Llama 3.2 1B Base Model cpt merged?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (1.6 GB file, about 2.3 GB in use).

Which Lekhansh Llama 3.2 1B Base Model cpt merged quant should you choose?

Q4_K_M is the usual starting point for Lekhansh Llama 3.2 1B Base Model cpt merged: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 1.6 GB, about 2.9 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.5B
Trained context131,072 tokens

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)94
Last updated2024-10-29

Frequently asked questions about Lekhansh Llama 3.2 1B Base Model cpt merged

How much VRAM does Lekhansh Llama 3.2 1B Base Model cpt merged need?

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.5 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 Lekhansh Llama 3.2 1B Base Model cpt merged on an 8 GB GPU?

Yes, with Q8_0: the 1.6 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Lekhansh Llama 3.2 1B Base Model cpt merged GGUF?

It depends on the quant: Q4_K_M is 0.5 GB, Q2_K is 0.7 GB, Q3_K is 0.7 GB, Q3_K_S is 0.8 GB, Q3_K_M is 0.8 GB, Q3_K_L is 0.8 GB and 13 more.

What context length does Lekhansh Llama 3.2 1B Base Model cpt merged support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download Lekhansh Llama 3.2 1B Base Model cpt merged GGUF?

The files are on Hugging Face in the RichardErkhov/Lekhansh_-_Llama-3.2-1B-Base-Model-cpt-merged-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other tiny models

All tiny models →