PY

Pythia 70m Deduped

PythiaGGUF by mradermacherUpdated 2024-09-08
Download on Hugging Face
Parameters70M
Context2K
Layers6
Architecturegptneox
Smallest quant0.0 GB
Quick answer

Pythia 70m Deduped needs about 0.6 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.0 GB (Q2_K) to 0.1 GB (F16).

Pythia 70m Deduped – 70M‑parameter GPT-NeoX model in GGUF format

Pythia 70m Deduped is a 70.4‑million‑parameter transformer trained on a deduplicated Pile dataset. It is available in multiple GGUF quantizations and licensed under Apache‑2.0. The model supports 2048‑token context and is optimized for research and lightweight inference.

Good at

  • Research‑grade interpretability
  • Low‑memory inference
  • Fast token generation

Limits

  • No vision support
  • Limited to 2048‑token context
  • Requires GPU for best performance

Best for

  • Academic experiments
  • Embedded inference on edge devices
  • Rapid prototyping of language models

Who it’s for. Researchers and developers needing a small, open‑source language model for experimentation or lightweight deployment. The model is suitable for those who prefer a GPT‑NeoX architecture and Apache‑2.0 licensing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.0 GB 0.6 GB
Fits Get file →
IQ3_XS0.0 GB 0.6 GB
Fits Get file →
IQ3_S0.0 GB 0.6 GB
Fits Get file →
Q3_K_S0.0 GB 0.6 GB
Fits Get file →
IQ3_M0.0 GB 0.6 GB
Fits Get file →
Q3_K_M0.0 GB 0.6 GB
Fits Get file →
Q3_K_L0.0 GB 0.6 GB
Fits Get file →
IQ4_XS0.0 GB 0.6 GB
Fits Get file →
Q4_K_S0.0 GB 0.6 GB
Fits Get file →
Q4_K_M0.0 GB 0.6 GB
Fits Get file →
Q5_K_S0.1 GB 0.6 GB
Fits Get file →
Q5_K_M0.1 GB 0.6 GB
Fits Get file →
Q6_K0.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.1 GB 0.7 GB
Fits Get file →

For 8‑GB VRAM, use Q4_K_M or Q4_K_S (0.05 GB file, ~0.6 GB memory). For 4‑GB VRAM, Q2_K or IQ3_XS (0.04 GB file, ~0.6 GB memory). For 2‑GB VRAM, Q2_K is recommended. Memory estimates are approximate.

What GPU do you need for Pythia 70m 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 F16 (0.1 GB file, about 0.7 GB in use).

Which Pythia 70m Deduped quant should you choose?

Q4_K_M is the usual starting point for Pythia 70m Deduped: it balances file size and quality well. Here it is a 0.0 GB file.

The Q8_0 file is 0.1 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 0.0 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
Parameters70M
Layers6
Trained context2,048 tokens
KV cache (fp16)12 KB per token

Source

Quantized bymradermacher
FamilyPythia
Licenseapache-2.0
Downloads (HF)636
Last updated2024-09-08

Frequently asked questions about Pythia 70m Deduped

How much VRAM does Pythia 70m Deduped need?

About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.0 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 70m Deduped on an 8 GB GPU?

Yes, with F16: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Pythia 70m Deduped GGUF?

It depends on the quant: Q2_K is 0.0 GB, IQ3_XS is 0.0 GB, IQ3_S is 0.0 GB, Q3_K_S is 0.0 GB, IQ3_M is 0.0 GB, Q3_K_M is 0.0 GB and 9 more.

What context length does Pythia 70m 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 0.1 GB at 8K and 0.0 GB at 2K.

Where can I download Pythia 70m Deduped GGUF?

The files are on Hugging Face in the mradermacher/pythia-70m-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 70m 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 70m Deduped on 4 GB VRAM?

Yes, using Q2_K or IQ3_XS quantizations will fit within 4 GB VRAM with ~0.6 GB memory usage.

Does this model support image inputs?

No, Pythia 70m Deduped is a text‑only language model.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of pythia-70m-deduped

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Pythia models

All Pythia →

Other tiny models

All tiny models →