AR

gguf q5 k l imat arcee lite

ArceeGGUF by FelladrinUpdated 2024-08-14
Download on Hugging Face
Parameters1.78B
Context32K
Layers28
Architectureqwen2
Smallest quant1.4 GB
Quick answer

gguf q5 k l imat arcee lite needs about 2.2 GB of memory at Q5_K_L (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.4 GB (Q5_K_L) to 1.4 GB (Q5_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

gguf q5 k l imat arcee lite is a 1.78B-parameter Arcee model in GGUF format, quantized by Felladrin. Its trained context length is 32K tokens. The repository has 2 quant files, from 1.4 GB (Q5_K_L) to 1.4 GB (Q5_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_L1.4 GB 2.2 GB
Fits Get file →
Q5_K_L1.4 GB (6 parts) 2.2 GB
Fits Get file →

What GPU do you need for gguf q5 k l imat arcee lite?

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 Q5_K_L (1.4 GB file, about 2.2 GB in use).

Which gguf q5 k l imat arcee lite quant should you choose?

Q5_K_L (1.4 GB) is the middle option in this repository. 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

Architectureqwen2
Parameters1.78B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized byFelladrin
FamilyArcee
Licenseapache-2.0
Downloads (HF)44
Last updated2024-08-14

Frequently asked questions about gguf q5 k l imat arcee lite

How much VRAM does gguf q5 k l imat arcee lite need?

About 2.2 GB at Q5_K_L with an 8K context window. That is the 1.4 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 gguf q5 k l imat arcee lite on an 8 GB GPU?

Yes, with Q5_K_L: the 1.4 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gguf q5 k l imat arcee lite GGUF?

It depends on the quant: Q5_K_L is 1.4 GB, Q5_K_L is 1.4 GB.

What context length does gguf q5 k l imat arcee lite support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download gguf q5 k l imat arcee lite GGUF?

The files are on Hugging Face in the Felladrin/gguf-q5_k_l-imat-arcee-lite repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gguf q5 k l imat arcee lite 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.

Other GGUFs of arcee-lite

Similar models

Browse all →

More from Felladrin

All by Felladrin →

More Arcee models

All Arcee →

Other tiny models

All tiny models →