PY

Pythia 12b Deduped

PythiaGGUF by mradermacherUpdated 2024-09-08
Download on Hugging Face
Parameters11.8B
Context2K
Layers36
Architecturegptneox
Smallest quant4.5 GB
Quick answer

Pythia 12b Deduped needs about 14.1 GB of memory at Q4_K_M (a 7.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 4.5 GB (Q2_K) to 12.6 GB (Q8_0).

Pythia 12b Deduped – 11.8B parameter transformer model

Pythia 12b Deduped is a 11.8B parameter GPT-NeoX based language model trained on a deduplicated Pile dataset. It supports 2048 token context and is released under Apache‑2.0. The model is available in multiple GGUF quantizations.

Good at

  • Large context generation
  • Research‑grade interpretability
  • Stable inference on GPUs

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is Apache‑2.0

Best for

  • Academic research on LLM interpretability
  • Fine‑tuning for niche NLP tasks
  • Benchmarking transformer models

Who it’s for. Researchers and developers needing a large, open‑source language model for experimentation. The model is suitable for those who can manage the memory requirements of the various quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.5 GB 6.5 GB
Fits Get file →
IQ3_XS5.1 GB 7.1 GB
Fits Get file →
IQ3_S5.2 GB 7.2 GB
Tight Get file →
Q3_K_S5.2 GB 7.2 GB
Tight Get file →
IQ3_M5.8 GB 7.8 GB
Tight Get file →
Q3_K_M6.2 GB 8.2 GB
Too big Get file →
IQ4_XS6.4 GB 8.5 GB
Too big Get file →
Q4_K_S6.8 GB 8.8 GB
Too big Get file →
Q3_K_L6.8 GB 8.8 GB
Too big Get file →
Q4_K_M7.6 GB 9.6 GB
Too big Get file →
Q5_K_S8.2 GB 10.2 GB
Too big Get file →
Q5_K_M8.8 GB 10.8 GB
Too big Get file →
Q6_K9.7 GB 11.7 GB
Too big Get file →
Q8_012.6 GB 14.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (7.58 GB file, ~14.1 GB memory). For 12 GB VRAM, Q5_K_M (8.82 GB file, ~15.4 GB memory) is a good balance. For 16 GB VRAM, Q6_K (9.73 GB file, ~16.3 GB memory) offers higher quality.

What GPU do you need for Pythia 12b 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ3_S (5.2 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (8.8 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.6 GB file, about 19.1 GB in use).

Which Pythia 12b Deduped quant should you choose?

Q4_K_M is the usual starting point for Pythia 12b Deduped: it balances file size and quality well. Here it is a 7.6 GB file.

The Q8_0 file is 12.6 GB, about 1.7 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 4.5 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
Parameters11.8B
Layers36
Trained context2,048 tokens
KV cache (fp16)720 KB per token

Source

Quantized bymradermacher
FamilyPythia
Licenseapache-2.0
Downloads (HF)1,737
Last updated2024-09-08

Frequently asked questions about Pythia 12b Deduped

How much VRAM does Pythia 12b Deduped need?

About 14.1 GB at Q4_K_M with an 8K context window. That is the 7.6 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 12b Deduped on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Pythia 12b Deduped GGUF?

It depends on the quant: Q2_K is 4.5 GB, IQ3_XS is 5.1 GB, IQ3_S is 5.2 GB, Q3_K_S is 5.2 GB, IQ3_M is 5.8 GB, Q3_K_M is 6.2 GB and 8 more.

What context length does Pythia 12b 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 6.0 GB at 8K and 1.5 GB at 2K.

Where can I download Pythia 12b Deduped GGUF?

The files are on Hugging Face in the mradermacher/pythia-12b-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 12b 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 12b Deduped on 8 GB VRAM?

Use the Q4_K_M quantization; it requires about 14.1 GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.

Is the model licensed for commercial use?

Yes, it is released under the Apache‑2.0 license, which allows commercial use.

Does the model support vision tasks?

No, the model is purely a language model with no vision capabilities.

Other GGUFs of pythia-12b-deduped

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Pythia models

All Pythia →

Other medium models

All medium models →