IP

gguf sharded IPythia 410m

IpythiaGGUF by FelladrinUpdated 2024-06-07
Download on Hugging Face
Parameters405M
Context2K
Layers24
Architecturegptneox
Smallest quant0.2 GB
Quick answer

gguf sharded IPythia 410m needs about 1.6 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.2 GB (Q2_K) to 0.4 GB (Q8_0).

gguf sharded IPythia 410m is a 405M-parameter Ipythia model in GGUF format, quantized by Felladrin. Its trained context length is 2K tokens. The repository has 10 quant files, from 0.2 GB (Q2_K) to 0.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB (4 parts) 0.9 GB
Fits Get file →
Q3_K_S0.2 GB (4 parts) 0.9 GB
Fits Get file →
Q3_K_M0.2 GB (5 parts) 0.9 GB
Fits Get file →
Q4_00.2 GB (5 parts) 0.9 GB
Fits Get file →
Q4_K_S0.2 GB (5 parts) 0.9 GB
Fits Get file →
Q4_K_M0.3 GB (5 parts) 1.0 GB
Fits Get file →
Q5_K_S0.3 GB (6 parts) 1.0 GB
Fits Get file →
Q5_K_M0.3 GB (6 parts) 1.0 GB
Fits Get file →
Q6_K0.3 GB (7 parts) 1.0 GB
Fits Get file →
Q8_00.4 GB (8 parts) 1.1 GB
Fits Get file →

What GPU do you need for gguf sharded IPythia 410m?

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 (0.4 GB file, about 1.7 GB in use).

Which gguf sharded IPythia 410m quant should you choose?

Q4_K_M is the usual starting point for gguf sharded IPythia 410m: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.4 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 0.2 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

Architecturegptneox
Parameters405M
Layers24
Trained context2,048 tokens
KV cache (fp16)96 KB per token

Source

Quantized byFelladrin
FamilyIpythia
Downloads (HF)95
Last updated2024-06-07

Frequently asked questions about gguf sharded IPythia 410m

How much VRAM does gguf sharded IPythia 410m need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.3 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 IPythia 410m on an 8 GB GPU?

Yes, with Q8_0: the 0.4 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gguf sharded IPythia 410m GGUF?

It depends on the quant: Q2_K is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, Q4_0 is 0.2 GB, Q4_K_S is 0.2 GB, Q4_K_M is 0.3 GB and 4 more.

What context length does gguf sharded IPythia 410m support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.2 GB at 2K.

Where can I download gguf sharded IPythia 410m GGUF?

The files are on Hugging Face in the Felladrin/gguf-sharded-IPythia-410m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of IPythia-410m

Similar models

Browse all →

More from Felladrin

All by Felladrin →

More Ipythia models

All Ipythia →

Other tiny models

All tiny models →