LL

2024NOV10 llama 3 1 8b model all

LlamaGGUF by CPSC532Updated 2024-11-13
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant1.9 GB
Quick answer

2024NOV10 llama 3 1 8b model all needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.9 GB (Q4_0) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

2024NOV10 llama 3 1 8b model all is a 3.21B-parameter Llama model in GGUF format, quantized by CPSC532. Its trained context length is 128K tokens. The repository has 5 quant files, from 1.9 GB (Q4_0) to 6.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →
BF166.4 GB 7.9 GB
Tight Get file →
F166.4 GB 7.9 GB
Tight Get file →

What GPU do you need for 2024NOV10 llama 3 1 8b model all?

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 Q4_K_M (2.0 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.4 GB file, about 7.9 GB in use).

Which 2024NOV10 llama 3 1 8b model all quant should you choose?

Q4_K_M is the usual starting point for 2024NOV10 llama 3 1 8b model all: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 3.4 GB, about 1.7 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 Q4_0 at 1.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byCPSC532
FamilyLlama
Licenseapache-2.0
Downloads (HF)26
Last updated2024-11-13

Frequently asked questions about 2024NOV10 llama 3 1 8b model all

How much VRAM does 2024NOV10 llama 3 1 8b model all need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 2024NOV10 llama 3 1 8b model all on an 8 GB GPU?

Yes, with BF16: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of 2024NOV10 llama 3 1 8b model all GGUF?

It depends on the quant: Q4_0 is 1.9 GB, Q4_K_M is 2.0 GB, Q8_0 is 3.4 GB, BF16 is 6.4 GB, F16 is 6.4 GB.

What context length does 2024NOV10 llama 3 1 8b model all support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download 2024NOV10 llama 3 1 8b model all GGUF?

The files are on Hugging Face in the CPSC532/2024NOV10_llama_3_1_8b_model_all repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does 2024NOV10 llama 3 1 8b model all 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.

Similar models

Browse all →

More from CPSC532

All by CPSC532 →

More Llama models

All Llama →

Other tiny models

All tiny models →