PY

Pythia 160m Deduped

PythiaGGUF by mradermacherUpdated 2024-09-08
Download on Hugging Face
Parameters162M
Context2K
Layers12
Architecturegptneox
Smallest quant0.1 GB
Quick answer

Pythia 160m Deduped 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 14 quants, from 0.1 GB (Q2_K) to 0.2 GB (Q8_0).

Pythia 160m Deduped – a small GPT-NeoX language model

Pythia 160m Deduped is a transformer‑based language model with 0.162 billion parameters. It was trained on the Pile dataset after global deduplication and supports a 2048‑token context window. The model is released under the Apache 2.0 license.

Good at

  • Interpretability research
  • Baseline performance for small GPT‑NeoX models
  • Low‑memory inference

Limits

  • No vision support
  • Limited to 2048‑token context
  • Requires a GGUF quantized file

Best for

  • Running on edge devices
  • Educational demos
  • Rapid prototyping of language models

Who it’s for. Researchers and developers who need a lightweight, open‑source language model for experimentation or educational purposes. The model is ideal for those who value interpretability and reproducibility.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.7 GB
Fits Get file →
IQ3_XS0.1 GB 0.7 GB
Fits Get file →
IQ3_S0.1 GB 0.7 GB
Fits Get file →
Q3_K_S0.1 GB 0.7 GB
Fits Get file →
IQ3_M0.1 GB 0.7 GB
Fits Get file →
Q3_K_M0.1 GB 0.7 GB
Fits Get file →
Q3_K_L0.1 GB 0.7 GB
Fits Get file →
IQ4_XS0.1 GB 0.7 GB
Fits Get file →
Q4_K_S0.1 GB 0.7 GB
Fits Get file →
Q4_K_M0.1 GB 0.7 GB
Fits Get file →
Q5_K_S0.1 GB 0.7 GB
Fits Get file →
Q5_K_M0.1 GB 0.7 GB
Fits Get file →
Q6_K0.1 GB 0.7 GB
Fits Get file →
Q8_00.2 GB 0.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 0.11 GB, memory 0.9 GB at 8k context). For 4 GB VRAM, choose Q3_K_S or IQ3_S (file size 0.09 GB, memory 0.9 GB). For 2 GB VRAM, the smallest options are Q2_K or IQ3_XS (file size 0.08–0.09 GB). Memory estimates are approximate.

What GPU do you need for Pythia 160m Deduped?

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 Pythia 160m Deduped quant should you choose?

Q4_K_M is the usual starting point for Pythia 160m Deduped: 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

Architecturegptneox
Parameters162M
Layers12
Trained context2,048 tokens
KV cache (fp16)36 KB per token

Source

Quantized bymradermacher
FamilyPythia
Licenseapache-2.0
Downloads (HF)1,609
Last updated2024-09-08

Frequently asked questions about Pythia 160m Deduped

How much VRAM does Pythia 160m Deduped 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 Pythia 160m Deduped 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 Pythia 160m Deduped GGUF?

It depends on the quant: Q2_K is 0.1 GB, IQ3_XS is 0.1 GB, IQ3_S is 0.1 GB, Q3_K_S is 0.1 GB, IQ3_M is 0.1 GB, Q3_K_M is 0.1 GB and 8 more.

What context length does Pythia 160m Deduped support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.1 GB at 2K.

Where can I download Pythia 160m Deduped GGUF?

The files are on Hugging Face in the mradermacher/pythia-160m-deduped-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 Pythia 160m Deduped 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.

Can I run Pythia 160m Deduped on 4 GB VRAM?

Yes, using the Q3_K_S or IQ3_S quantized file, which requires about 0.9 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model is purely a language model and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of pythia-160m-deduped

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Pythia models

All Pythia →

Other tiny models

All tiny models →