Gpt Neox 20b needs about 22.5 GB of memory at Q4_K_M (a 13.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.4 GB (IQ1_S) to 16.9 GB (Q6_K).
GPT-NeoX-20B 20B‑parameter autoregressive model in GGUF format
GPT-NeoX-20B is a 20.6 billion‑parameter transformer trained on the Pile. The GGUF version is available in multiple quantizations, each with a distinct file size and memory requirement. The model is licensed under Apache 2.0 and is intended for research and fine‑tuning, not for direct deployment.
Good at
- Large‑scale language modeling
- Research‑grade feature extraction
- Fine‑tuning foundation
Limits
- English‑only, no vision
- Not suitable for unsupervised deployment
- Requires 8 k context for estimates
Best for
- Academic research on language models
- Fine‑tuning for downstream NLP tasks
- Benchmarking transformer architectures
Who it’s for. Researchers and developers who need a large‑parameter language model for experimentation or fine‑tuning. The model is not intended for production chatbots or human‑facing applications without supervision.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.4 GB | 7.1 GB | Fits | Get file → | |
| IQ1_M | 4.8 GB | 7.6 GB | Tight | Get file → | |
| IQ2_XXS | 5.5 GB | 8.2 GB | Too big | Get file → | |
| IQ2_XS | 6.1 GB | 8.8 GB | Too big | Get file → | |
| IQ2_S | 6.5 GB | 9.2 GB | Too big | Get file → | |
| IQ2_M | 7.0 GB | 9.7 GB | Too big | Get file → | |
| Q2_K | 7.8 GB | 10.5 GB | Too big | Get file → | |
| IQ3_XXS | 8.1 GB | 10.8 GB | Too big | Get file → | |
| IQ3_XS | 8.7 GB | 11.4 GB | Too big | Get file → | |
| IQ3_S | 9.0 GB | 11.7 GB | Too big | Get file → | |
| Q3_K_S | 9.0 GB | 11.7 GB | Too big | Get file → | |
| IQ3_M | 10.0 GB | 12.7 GB | Too big | Get file → | |
| Q3_K_M | 10.8 GB | 13.5 GB | Too big | Get file → | |
| IQ4_XS | 11.0 GB | 13.7 GB | Too big | Get file → | |
| Q4_0 | 11.7 GB | 14.4 GB | Too big | Get file → | |
| Q4_K_S | 11.8 GB | 14.5 GB | Too big | Get file → | |
| Q3_K_L | 11.8 GB | 14.5 GB | Too big | Get file → | |
| Q4_K_M | 13.1 GB | 15.8 GB | Too big | Get file → | |
| Q5_K_S | 14.2 GB | 16.9 GB | Too big | Get file → | |
| Q5_K_M | 15.3 GB | 18.0 GB | Too big | Get file → | |
| Q6_K | 16.9 GB | 19.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.43 GB file, 13.8 GB memory) or IQ1_M (4.84 GB, 14.2 GB). If 12 GB VRAM is available, IQ2_S (6.46 GB, 15.8 GB) or Q2_K (7.76 GB, 17.1 GB) are suitable. Higher quants such as Q4_K_M (13.14 GB, 22.5 GB) require more memory but offer better quality.
What GPU do you need for Gpt Neox 20b?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ2_S (6.5 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_S (14.2 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (16.9 GB file, about 26.2 GB in use).
Which Gpt Neox 20b quant should you choose?
Q4_K_M is the usual starting point for Gpt Neox 20b: it balances file size and quality well. Here it is a 13.1 GB file.
If memory is tight, the smallest file is IQ1_S at 4.4 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 Gpt Neox 20b
How much VRAM does Gpt Neox 20b need?
About 22.5 GB at Q4_K_M with an 8K context window. That is the 13.1 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 Gpt Neox 20b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gpt Neox 20b GGUF?
It depends on the quant: IQ1_S is 4.4 GB, IQ1_M is 4.8 GB, IQ2_XXS is 5.5 GB, IQ2_XS is 6.1 GB, IQ2_S is 6.5 GB, IQ2_M is 7.0 GB and 15 more.
What context length does Gpt Neox 20b support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 8.9 GB at 8K and 2.2 GB at 2K.
Where can I download Gpt Neox 20b GGUF?
The files are on Hugging Face in the mradermacher/gpt-neox-20b-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 Gpt Neox 20b 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 GPT-NeoX-20B on 8 GB VRAM?
Yes, with IQ1_S or IQ1_M quantizations, which use about 13.8–14.2 GB of VRAM at 8 k context.
Is this model suitable for production chatbots?
No. The model is not fine‑tuned for human‑facing interactions and should not be deployed without supervision.
What license does the GGUF version use?
The GGUF files are released under the Apache 2.0 license.