Pythia 2.8b Deduped needs about 5.0 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 0.7 GB (IQ1_S) to 2.3 GB (Q6_K).
Pythia 2.8b Deduped – a 2.8B‑parameter GPT-NeoX model in GGUF format
Pythia 2.8b Deduped is a transformer‑based language model with 2.8 billion parameters. It is trained on a globally deduplicated version of the Pile dataset and is available in multiple GGUF quantizations. The model supports 2048‑token context windows and is released under the Apache 2.0 license.
Good at
- Large‑scale language modeling
- Research‑grade interpretability
- Open‑source community use
Limits
- No vision or multimodal support
- Requires 8 k context for memory estimates
- License is Apache 2.0
Best for
- Academic research on LLM interpretability
- Fine‑tuning on custom text corpora
- Benchmarking quantization effects
Who it’s for. Researchers and developers who need a mid‑size, open‑source language model for experimentation. The model is suitable for those who prefer a deduplicated dataset and want to explore different quantization strategies.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.7 GB | 1.8 GB | Fits | Get file → | |
| IQ1_M | 0.7 GB | 1.9 GB | Fits | Get file → | |
| IQ2_XXS | 0.8 GB | 2.0 GB | Fits | Get file → | |
| IQ2_XS | 0.9 GB | 2.0 GB | Fits | Get file → | |
| IQ2_S | 0.9 GB | 2.1 GB | Fits | Get file → | |
| IQ2_M | 1.0 GB | 2.2 GB | Fits | Get file → | |
| Q2_K | 1.1 GB | 2.3 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 2.3 GB | Fits | Get file → | |
| IQ3_XS | 1.2 GB | 2.4 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 2.4 GB | Fits | Get file → | |
| IQ3_M | 1.4 GB | 2.5 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 2.6 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_L | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_K_M | 1.8 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_M | 2.1 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.3 GB | 3.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (1.6 GB file, ~4.8 GB VRAM). For 6 GB VRAM, IQ2_S (0.92 GB file, ~4.1 GB VRAM). For 4 GB VRAM, IQ1_S (0.66 GB file, ~3.8 GB VRAM). Memory estimates are approximate.
What GPU do you need for Pythia 2.8b 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 IQ2_XXS (0.8 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (2.3 GB file, about 5.5 GB in use).
Which Pythia 2.8b Deduped quant should you choose?
Q4_K_M is the usual starting point for Pythia 2.8b Deduped: it balances file size and quality well. Here it is a 1.8 GB file.
If memory is tight, the smallest file is IQ1_S at 0.7 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
Source
Frequently asked questions about Pythia 2.8b Deduped
How much VRAM does Pythia 2.8b Deduped need?
About 5.0 GB at Q4_K_M with an 8K context window. That is the 1.8 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 2.8b Deduped on an 8 GB GPU?
Yes, with Q6_K: the 2.3 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Pythia 2.8b Deduped GGUF?
It depends on the quant: IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ2_S is 0.9 GB, IQ2_M is 1.0 GB and 18 more.
What context length does Pythia 2.8b 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 2.7 GB at 8K and 0.7 GB at 2K.
Where can I download Pythia 2.8b Deduped GGUF?
The files are on Hugging Face in the mradermacher/pythia-2.8b-deduped-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 2.8b 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 2.8b Deduped on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 4.8 GB VRAM at 8 k context, which fits within an 8 GB GPU.
Is the model licensed for commercial use?
The model is released under the Apache 2.0 license, which allows commercial use with attribution.
Does the model support image inputs?
No, Pythia 2.8b Deduped is a text‑only transformer and does not support vision or multimodal inputs.