LL

Models Mlx Community Llama 3.2 3B Bf16

LlamaGGUF by MaziyarPanahiUpdated 2024-11-02
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant2.3 GB
Quick answer

Models Mlx Community Llama 3.2 3B Bf16 needs about 4.1 GB of memory at BF16 (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.3 GB (BF16) to 6.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Models Mlx Community Llama 3.2 3B Bf16 is a 3.21B-parameter Llama model in GGUF format, quantized by MaziyarPanahi. Its trained context length is 128K tokens. The repository has 5 quant files, from 2.3 GB (BF16) to 6.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF162.3 GB 3.7 GB
Fits Get file →
BF162.3 GB 3.8 GB
Fits Get file →
BF162.6 GB 4.1 GB
Fits Get file →
BF163.4 GB 4.9 GB
Fits Get file →
BF166.4 GB 7.9 GB
Tight Get file →

What GPU do you need for Models Mlx Community Llama 3.2 3B Bf16?

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 BF16 (2.3 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (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 Models Mlx Community Llama 3.2 3B Bf16 quant should you choose?

BF16 (2.6 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 BF16 at 2.3 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 byMaziyarPanahi
FamilyLlama
Licensellama3.2
Downloads (HF)373
Last updated2024-11-02

Frequently asked questions about Models Mlx Community Llama 3.2 3B Bf16

How much VRAM does Models Mlx Community Llama 3.2 3B Bf16 need?

About 4.1 GB at BF16 with an 8K context window. That is the 2.6 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 Models Mlx Community Llama 3.2 3B Bf16 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 Models Mlx Community Llama 3.2 3B Bf16 GGUF?

It depends on the quant: BF16 is 2.3 GB, BF16 is 2.3 GB, BF16 is 2.6 GB, BF16 is 3.4 GB, BF16 is 6.4 GB.

What context length does Models Mlx Community Llama 3.2 3B Bf16 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 Models Mlx Community Llama 3.2 3B Bf16 GGUF?

The files are on Hugging Face in the MaziyarPanahi/Llama-3.2-3B-bf16-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 Models Mlx Community Llama 3.2 3B Bf16 use?

Hugging Face lists the license as llama3.2. 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 MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other tiny models

All tiny models →