LL

LLM

LlmGGUF by zhuipiaochenUpdated 2024-06-11
Download on Hugging Face
Parameters7.51B
Context128K
Layers32
Architecturephi3
Smallest quant0.5 GB
Quick answer

LLM needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 10 quants, from 0.5 GB (Q5_K_M) to 5.4 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

LLM is a 7.51B-parameter Llm model in GGUF format, quantized by zhuipiaochen. Its trained context length is 128K tokens. The repository has 10 quant files, from 0.5 GB (Q5_K_M) to 5.4 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.5 GB 4.2 GB
Fits Get file →
Q4_01.1 GB 4.8 GB
Fits Get file →
Q4_K_M2.4 GB 6.1 GB
Fits Get file →
Q8_02.7 GB 6.4 GB
Fits Get file →
Q4_03.5 GB 7.2 GB
Tight Get file →
Q4_K_M4.1 GB 7.8 GB
Tight Get file →
Q4_K_M4.6 GB 8.3 GB
Too big Get file →
Q4_K_M4.6 GB 8.3 GB
Too big Get file →
Q4_K_M4.9 GB 8.6 GB
Too big Get file →
Q5_K_M5.4 GB 9.2 GB
Too big Get file →

What GPU do you need for LLM?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_0 (1.1 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (5.4 GB file, about 9.2 GB in use).

Which LLM quant should you choose?

Q4_K_M is the usual starting point for LLM: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 2.7 GB, about 1.1 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 Q5_K_M at 0.5 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters7.51B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byzhuipiaochen
FamilyLlm
Downloads (HF)83
Last updated2024-06-11

Frequently asked questions about LLM

How much VRAM does LLM need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LLM GGUF?

It depends on the quant: Q5_K_M is 0.5 GB, Q4_0 is 1.1 GB, Q4_K_M is 2.4 GB, Q8_0 is 2.7 GB, Q4_0 is 3.5 GB, Q4_K_M is 4.1 GB and 4 more.

What context length does LLM support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download LLM GGUF?

The files are on Hugging Face in the zhuipiaochen/LLM 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 Llm models

All Llm →

Other small models

All small models →