Pythia 6.9b needs about 9.2 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.5 GB (IQ1_S) to 5.6 GB (Q6_K).
Pythia 6.9b – 6.86B parameter GPT-NeoX model in GGUF format
Pythia 6.9b is a 6.86B parameter transformer model trained on the Pile. It is part of the Pythia Scaling Suite and is available in multiple GGUF quantizations. The model is released under the Apache 2.0 license.
Good at
- Large context handling
- Reasoning tasks
- Text generation
Limits
- No vision support
- Requires 8k context for estimates
- License is Apache 2.0
Best for
- Research on interpretability
- Benchmarking language models
- Educational demos
Who it’s for. Researchers and developers who need a large language model for experimentation and educational purposes. The model is suitable for those who can manage the memory requirements of the various quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.5 GB | 3.1 GB | Fits | Get file → | |
| IQ1_M | 1.7 GB | 3.3 GB | Fits | Get file → | |
| IQ2_XXS | 1.9 GB | 3.5 GB | Fits | Get file → | |
| IQ2_XS | 2.1 GB | 3.7 GB | Fits | Get file → | |
| IQ2_S | 2.2 GB | 3.8 GB | Fits | Get file → | |
| IQ2_M | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q2_K | 2.6 GB | 4.2 GB | Fits | Get file → | |
| IQ3_XXS | 2.7 GB | 4.3 GB | Fits | Get file → | |
| IQ3_XS | 3.0 GB | 4.5 GB | Fits | Get file → | |
| IQ3_S | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_S | 3.0 GB | 4.6 GB | Fits | Get file → | |
| IQ3_M | 3.4 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_M | 3.6 GB | 5.2 GB | Fits | Get file → | |
| IQ4_XS | 3.7 GB | 5.3 GB | Fits | Get file → | |
| Q4_0 | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_L | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q4_K_S | 4.0 GB | 5.5 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_S | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.1 GB | 6.7 GB | Fits | Get file → | |
| Q6_K | 5.6 GB | 7.2 GB | Tight | Get file → |
For 8 GB VRAM, use IQ1_S (file size 1.55 GB, estimated 6.3 GB memory). For 12 GB VRAM, Q4_K_M (file size 4.4 GB, estimated 9.2 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (file size 5.11 GB, estimated 9.9 GB memory) offers higher quality.
What GPU do you need for Pythia 6.9b?
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: the best quant that fits is IQ3_S (3.0 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.6 GB file, about 10.4 GB in use).
Which Pythia 6.9b quant should you choose?
Q4_K_M is the usual starting point for Pythia 6.9b: it balances file size and quality well. Here it is a 4.4 GB file.
If memory is tight, the smallest file is IQ1_S at 1.5 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
Source
Frequently asked questions about Pythia 6.9b
How much VRAM does Pythia 6.9b need?
About 9.2 GB at Q4_K_M with an 8K context window. That is the 4.4 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 6.9b on an 8 GB GPU?
Yes, with IQ3_S: the 3.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Pythia 6.9b GGUF?
It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.1 GB, IQ2_S is 2.2 GB, IQ2_M is 2.4 GB and 18 more.
What context length does Pythia 6.9b support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.
Where can I download Pythia 6.9b GGUF?
The files are on Hugging Face in the mradermacher/pythia-6.9b-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 6.9b 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 6.9b on 8 GB VRAM?
Yes, the IQ1_S quantization requires about 6.3 GB memory at 8k context, which fits in 8 GB VRAM.
Does this model support vision tasks?
No, Pythia 6.9b is a text-only transformer model.
What license applies to this model?
The model is released under the Apache 2.0 license.