Skip to content
Weights Not Walls
Menu

EleutherAI

gpt-neox-20b

Reviewed
Size
20.7B parameterscounted from the safetensors header on the Hub
Licence
unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
On the Hub since
7 Apr 2022the date the repo was created
Context length
2k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)GPTNeoXForCausalLM
On Hugging Face
EleutherAI/gpt-neox-20b278k downloads in the last 30 days, 587 likes

Scores

6 independent results on 6 eval sets
ARC AI2Reported

Epoch's name: gpt-neox-20b. Best closed model on this set: gpt-3.5-turbo-1106, 87.4% (OpenAI). All 134 results

BoolQReported

Epoch's name: gpt-neox-20b. Best closed model on this set: Inflection-1, 89.7% (Inflection AI). All 136 results

HellaSwagReported

Epoch's name: gpt-neox-20b. Best closed model on this set: gpt-4-0314, 95.3% (OpenAI). All 113 results

OpenBookQAReported

Epoch's name: gpt-neox-20b. Best closed model on this set: gpt-3.5-turbo-1106, 86.0% (OpenAI). All 70 results

PIQAReported

Epoch's name: gpt-neox-20b. Best closed model on this set: gpt-4o-mini-2024-07-18, 88.7% (OpenAI). All 113 results

WinograndeReported

Epoch's name: gpt-neox-20b. Best closed model on this set: claude-3-opus-20240229, 88.5% (Anthropic). All 137 results

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 8.3 GB, worked out from the model's config (EleutherAI/gpt-neox-20b), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

mradermacher/gpt-neox-20b-i1-GGUF (converted by mradermacher), 1.1k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
IQ3_XXS7.5 GBfile size16.3 GB7.5 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:IQ3_XXS
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:IQ3_XXS
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-IQ3_XXS.gguf" --local-dir gpt-neox-20b-i1-GGUF
IQ3_XS8.1 GBfile size16.9 GB8.1 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:IQ3_XS
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:IQ3_XS
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-IQ3_XS.gguf" --local-dir gpt-neox-20b-i1-GGUF
IQ3_S8.4 GBfile size17.1 GB8.4 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:IQ3_S
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:IQ3_S
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-IQ3_S.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q3_K_S8.4 GBfile size17.1 GB8.4 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q3_K_S
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q3_K_S
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q3_K_S.gguf" --local-dir gpt-neox-20b-i1-GGUF
IQ3_M9.3 GBfile size18.0 GB9.3 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:IQ3_M
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:IQ3_M
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-IQ3_M.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q3_K_M10.0 GBfile size18.8 GB10.0 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q3_K_M
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q3_K_M
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q3_K_M.gguf" --local-dir gpt-neox-20b-i1-GGUF
IQ4_XS10.3 GBfile size19.0 GB10.3 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:IQ4_XS
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:IQ4_XS
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-IQ4_XS.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q4_010.9 GBfile size19.6 GB10.9 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q4_0
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q4_0
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q4_0.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q4_K_S10.9 GBfile size19.7 GB10.9 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q4_K_S
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q4_K_S
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q4_K_S.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q3_K_L11.0 GBfile size19.7 GB11.0 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q3_K_L
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q3_K_L
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q3_K_L.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q4_K_M12.2 GBfile size21.0 GB12.2 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q4_K_M
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q4_K_M
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q4_K_M.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q5_K_S13.2 GBfile size22.0 GB13.2 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q5_K_S
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q5_K_S
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q5_K_S.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q5_K_M14.2 GBfile size23.0 GB14.2 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q5_K_M
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q5_K_M
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q5_K_M.gguf" --local-dir gpt-neox-20b-i1-GGUF
Q6_K15.7 GBfile size24.5 GB15.7 + 8.3 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gpt-neox-20b-i1-GGUF:Q6_K
Ollama
ollama run hf.co/mradermacher/gpt-neox-20b-i1-GGUF:Q6_K
Download
hf download mradermacher/gpt-neox-20b-i1-GGUF --include "gpt-neox-20b.i1-Q6_K.gguf" --local-dir gpt-neox-20b-i1-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitnhe-ai/gpt-neox-20b-mlx-4Bit10.8 GBfile size19.5 GB10.8 + 8.3 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
F16original weights38.5 GBfile size47.2 GB38.5 + 8.3 + 0.50
hf download EleutherAI/gpt-neox-20b --local-dir gpt-neox-20b
Other conversions (1; sizes not read)

The Hub tags 9 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.