LL

llm.js

LlmGGUF by rahuldshettyUpdated 2024-01-08
Download on Hugging Face
Parameters462M
Context1K
Layers24
Architecturellama
Smallest quant0.3 GB
Quick answer

llm.js needs about 0.9 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB (Q8_0) to 0.5 GB (Q2_K).

llm.js is a 462M-parameter Llm model in GGUF format, quantized by rahuldshetty. Its trained context length is 1K tokens. The repository has 4 quant files, from 0.3 GB (Q8_0) to 0.5 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.3 GB 0.8 GB
Fits Get file →
Q4_K_M0.3 GB 0.8 GB
Fits Get file →
Q2_K0.5 GB 1.0 GB
Fits Get file →
Q2_K0.5 GB 1.0 GB
Fits Get file →

What GPU do you need for llm.js?

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 Q2_K (0.5 GB file, about 1.1 GB in use).

Which llm.js quant should you choose?

Q4_K_M is the usual starting point for llm.js: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.3 GB, about 0.9 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.

If memory is tight, the smallest file is Q8_0 at 0.3 GB, with the quality trade-offs that come with fewer bits. 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
Parameters462M
Layers24
Trained context1,024 tokens
KV cache (fp16)12 KB per token

Source

Quantized byrahuldshetty
FamilyLlm
Downloads (HF)35
Last updated2024-01-08

Frequently asked questions about llm.js

How much VRAM does llm.js need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.3 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 llm.js on an 8 GB GPU?

Yes, with Q2_K: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llm.js GGUF?

It depends on the quant: Q8_0 is 0.3 GB, Q4_K_M is 0.3 GB, Q2_K is 0.5 GB, Q2_K is 0.5 GB.

What context length does llm.js support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 1K.

Where can I download llm.js GGUF?

The files are on Hugging Face in the rahuldshetty/llm.js 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 rahuldshetty

All by rahuldshetty →

More Llm models

All Llm →

Other tiny models

All tiny models →