AI

gguf sharded Aira 2 124M DPO

AiraGGUF by FelladrinUpdated 2024-06-07
Download on Hugging Face
Parameters163M
Context1K
Layers12
Architecturegpt2
Smallest quant0.1 GB
Quick answer

gguf sharded Aira 2 124M DPO needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.1 GB (Q2_K) to 0.2 GB (Q8_0).

gguf sharded Aira 2 124M DPO is a 163M-parameter Aira model in GGUF format, quantized by Felladrin. Its trained context length is 1K tokens. The repository has 10 quant files, from 0.1 GB (Q2_K) to 0.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB (3 parts) 0.6 GB
Fits Get file →
Q3_K_S0.1 GB (3 parts) 0.6 GB
Fits Get file →
Q3_K_M0.1 GB (3 parts) 0.6 GB
Fits Get file →
Q4_00.1 GB (3 parts) 0.6 GB
Fits Get file →
Q4_K_S0.1 GB (3 parts) 0.6 GB
Fits Get file →
Q4_K_M0.1 GB (3 parts) 0.7 GB
Fits Get file →
Q5_K_S0.1 GB (4 parts) 0.7 GB
Fits Get file →
Q5_K_M0.1 GB (4 parts) 0.7 GB
Fits Get file →
Q6_K0.1 GB (4 parts) 0.7 GB
Fits Get file →
Q8_00.2 GB (5 parts) 0.7 GB
Fits Get file →

What GPU do you need for gguf sharded Aira 2 124M DPO?

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 Q8_0 (0.2 GB file, about 1.0 GB in use).

Which gguf sharded Aira 2 124M DPO quant should you choose?

Q4_K_M is the usual starting point for gguf sharded Aira 2 124M DPO: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.2 GB, about 1.6 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 Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt2
Parameters163M
Layers12
Trained context1,024 tokens
KV cache (fp16)36 KB per token

Source

Quantized byFelladrin
FamilyAira
Licenseapache-2.0
Downloads (HF)56
Last updated2024-06-07

Frequently asked questions about gguf sharded Aira 2 124M DPO

How much VRAM does gguf sharded Aira 2 124M DPO need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 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 sharded Aira 2 124M DPO on an 8 GB GPU?

Yes, with Q8_0: the 0.2 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gguf sharded Aira 2 124M DPO GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q4_0 is 0.1 GB, Q4_K_S is 0.1 GB, Q4_K_M is 0.1 GB and 4 more.

What context length does gguf sharded Aira 2 124M DPO support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 1K.

Where can I download gguf sharded Aira 2 124M DPO GGUF?

The files are on Hugging Face in the Felladrin/gguf-sharded-Aira-2-124M-DPO 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 sharded Aira 2 124M DPO 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 Aira-2-124M-DPO

Similar models

Browse all →

More from Felladrin

All by Felladrin →

More Aira models

All Aira →

Other tiny models

All tiny models →