LL

reception llama 3.2 3b test 1

LlamaGGUF by kholiavkoUpdated 2024-09-26
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant3.4 GB
Quick answer

reception llama 3.2 3b test 1 needs about 7.9 GB of memory at BF16 (a 6.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 3.4 GB (Q8_0) to 12.9 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

reception llama 3.2 3b test 1 is a 3.21B-parameter Llama model in GGUF format, quantized by kholiavko. Its trained context length is 128K tokens. The repository has 3 quant files, from 3.4 GB (Q8_0) to 12.9 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.4 GB 4.9 GB
Fits Get file →
BF166.4 GB 7.9 GB
Tight Get file →
F3212.9 GB 14.3 GB
Too big Get file →

What GPU do you need for reception llama 3.2 3b test 1?

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 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).
  • 12 GB VRAM: the best quant that fits is BF16 (6.4 GB file, about 7.9 GB in use).
  • 16 GB VRAM: the best quant that fits is F32 (12.9 GB file, about 14.3 GB in use).

Which reception llama 3.2 3b test 1 quant should you choose?

BF16 (6.4 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 3.4 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
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bykholiavko
FamilyLlama
Licenseapache-2.0
Downloads (HF)34
Last updated2024-09-26

Frequently asked questions about reception llama 3.2 3b test 1

How much VRAM does reception llama 3.2 3b test 1 need?

About 7.9 GB at BF16 with an 8K context window. That is the 6.4 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 reception llama 3.2 3b test 1 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 reception llama 3.2 3b test 1 GGUF?

It depends on the quant: Q8_0 is 3.4 GB, BF16 is 6.4 GB, F32 is 12.9 GB.

What context length does reception llama 3.2 3b test 1 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 reception llama 3.2 3b test 1 GGUF?

The files are on Hugging Face in the kholiavko/reception-llama-3.2-3b-test-1-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does reception llama 3.2 3b test 1 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 kholiavko

All by kholiavko →

More Llama models

All Llama →

Other tiny models

All tiny models →