MU

multillama 3.2 merge Q4 K M

MultillamaGGUF by SFBAIUpdated 2024-12-29
Download on Hugging Face
Parameters3.61B
Context128K
Layers28
Architecturellama
Smallest quant2.2 GB
Quick answer

multillama 3.2 merge Q4 K M needs about 3.7 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

multillama 3.2 merge Q4 K M is a 3.61B-parameter Multillama model in GGUF format, quantized by SFBAI. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.2 GB (Q4_K_M) to 2.2 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.2 GB 3.7 GB
Fits Get file →

What GPU do you need for multillama 3.2 merge Q4 K M?

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 (2.2 GB file, about 3.7 GB in use).

Which multillama 3.2 merge Q4 K M quant should you choose?

Q4_K_M is the usual starting point for multillama 3.2 merge Q4 K M: it balances file size and quality well. Here it is a 2.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.61B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bySFBAI
Downloads (HF)13
Last updated2024-12-29

Frequently asked questions about multillama 3.2 merge Q4 K M

How much VRAM does multillama 3.2 merge Q4 K M need?

About 3.7 GB at Q4_K_M with an 8K context window. That is the 2.2 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 multillama 3.2 merge Q4 K M on an 8 GB GPU?

Yes, with Q4_K_M: the 2.2 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of multillama 3.2 merge Q4 K M GGUF?

It depends on the quant: Q4_K_M is 2.2 GB.

What context length does multillama 3.2 merge Q4 K M 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 multillama 3.2 merge Q4 K M GGUF?

The files are on Hugging Face in the SFBAI/multillama-3.2-merge-Q4_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of multillama-3.2-merge

Similar models

Browse all →

More from SFBAI

All by SFBAI →

More Multillama models

All Multillama →

Other small models

All small models →