PY

Pythia 1b

PythiaGGUF by mradermacherUpdated 2024-09-08
Download on Hugging Face
Parameters1.01B
Context2K
Layers16
Architecturegptneox
Smallest quant0.3 GB
Quick answer

Pythia 1b needs about 2.2 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.3 GB (IQ1_S) to 0.8 GB (Q6_K).

Pythia 1b – 1 billion‑parameter GPT-NeoX model in GGUF format

Pythia 1b is a 1 billion‑parameter transformer trained on the Pile. It is available in multiple GGUF quantizations and licensed under Apache 2.0. The model supports a 2048‑token context window.

Good at

  • Interpretability research
  • Baseline for small‑scale LLM studies
  • Open‑source community use

Limits

  • No vision support
  • Limited to 2048‑token context
  • Requires GPU for efficient inference

Best for

  • Running on 8 GB VRAM with Q4_K_M
  • Fine‑tuning small datasets
  • Benchmarking quantization effects

Who it’s for. Developers and researchers who need a lightweight, open‑source language model for experimentation. The model is suitable for those who want to explore interpretability or run inference on modest hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.3 GB 1.0 GB
Fits Get file →
IQ1_M0.3 GB 1.1 GB
Fits Get file →
IQ2_XXS0.3 GB 1.1 GB
Fits Get file →
IQ2_XS0.3 GB 1.1 GB
Fits Get file →
IQ2_S0.4 GB 1.1 GB
Fits Get file →
IQ2_M0.4 GB 1.2 GB
Fits Get file →
Q2_K0.4 GB 1.2 GB
Fits Get file →
IQ3_XXS0.4 GB 1.2 GB
Fits Get file →
IQ3_XS0.5 GB 1.2 GB
Fits Get file →
IQ3_S0.5 GB 1.2 GB
Fits Get file →
Q3_K_S0.5 GB 1.2 GB
Fits Get file →
IQ3_M0.5 GB 1.3 GB
Fits Get file →
Q3_K_M0.6 GB 1.3 GB
Fits Get file →
IQ4_XS0.6 GB 1.3 GB
Fits Get file →
Q3_K_L0.6 GB 1.4 GB
Fits Get file →
Q4_00.6 GB 1.4 GB
Fits Get file →
Q4_00.6 GB 1.4 GB
Fits Get file →
Q4_00.6 GB 1.4 GB
Fits Get file →
Q4_00.6 GB 1.4 GB
Fits Get file →
Q4_K_S0.6 GB 1.4 GB
Fits Get file →
Q4_K_M0.7 GB 1.4 GB
Fits Get file →
Q5_K_S0.7 GB 1.5 GB
Fits Get file →
Q5_K_M0.8 GB 1.5 GB
Fits Get file →
Q6_K0.8 GB 1.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.66 GB file, ~2.2 GB VRAM at 8k context). If 6 GB VRAM is available, Q3_K_M (0.55 GB file, ~2.1 GB VRAM) is a good balance. For 4 GB VRAM, IQ1_S (0.27 GB file, ~1.8 GB VRAM) is recommended.

What GPU do you need for Pythia 1b?

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 Q6_K (0.8 GB file, about 2.4 GB in use).

Which Pythia 1b quant should you choose?

Q4_K_M is the usual starting point for Pythia 1b: it balances file size and quality well. Here it is a 0.7 GB file.

If memory is tight, the smallest file is IQ1_S at 0.3 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
Parameters1.01B
Layers16
Trained context2,048 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyPythia
Licenseapache-2.0
Downloads (HF)3,879
Last updated2024-09-08

Frequently asked questions about Pythia 1b

How much VRAM does Pythia 1b need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 0.7 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 1b on an 8 GB GPU?

Yes, with Q6_K: the 0.8 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Pythia 1b GGUF?

It depends on the quant: IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_XS is 0.3 GB, IQ2_S is 0.4 GB, IQ2_M is 0.4 GB and 18 more.

What context length does Pythia 1b support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.3 GB at 2K.

Where can I download Pythia 1b GGUF?

The files are on Hugging Face in the mradermacher/pythia-1b-i1-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 1b 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 1b on 8 GB VRAM?

Yes, use a quantization such as Q4_K_M or Q3_K_M which fit within 8 GB VRAM at 8k context.

Does Pythia 1b support image inputs?

No, the model only handles text and has no vision capabilities.

Other GGUFs of pythia-1b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Pythia models

All Pythia →

Other tiny models

All tiny models →