Zyte-1B

+ contribute

Zyte-1B is an open-weights language model from venkycs (aihub-app), released January 2024. Its published size is 1.1B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo venkycs/Zyte-1B @ac68485 (requested as aihub-app/zyte-1B, which the HF API redirects to venkycs/Zyte-1B): licence tag apache-2.0. 1,100,048,384 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-01: month the maker's Hugging Face repo was created (createdAt 2024-01-10).

8.2±2.4#709 of 719 LLMsfrom 3 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Zyte-1B, out of 828 with a score.

#	model	score	where	RAM	released
816	GPT-3 ada (API base model) OpenAI	10±2	comparison only		2020-06
817	StableLM-Base-Alpha 7B Stability AI	9±1	local	~35GB	2023-04
818	Zyte-1B venkycs (aihub-app)	8±2	local	~2.2GB	2024-01
819	GPT-Neo 125M EleutherAI	5±5	local	~2.1GB	2021-03
820	BLOOM 560M BigScience	5±2	local	~2.1GB	2022-07

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▃▁▁▃▆██▇▆▄▃▁ #458 of 458 · 97% of its score · 3 tests

test	result	vs the others in its run	difficulty	counts	why
HumanEval	2.4% ✎	▃·▁▁▃▄▆▅█▃▁▁ beats 0/99	easy · avg 79%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 41%	sharp · too hard for it
HumanEval+	1.8% ✎	▃·▁▁▁▃▄▄▄█▃▁ beats 0/99	easy · avg 74%	▇▇▇▇▇▇▇▇▇▇▇ 29%	sharp · too hard for it
MBPP+	7.5% ✎	▃···▁▁▂▅▇█▆▂ beats 0/75	easy · avg 68%	▇▇▇▇▇▇▇▇▇▇▇ 28%	typical

$ where to run it

llama.cpp · recommended

version

Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
macOS / Linux
curl -LsSf https://llama.app/install.sh | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run Zyte-1B · needs ~0.7 GB · from huggingface.co/mradermacher
chat in the terminal
llama cli -hf mradermacher/Zyte-1B-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/Zyte-1B-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Zyte-1B · needs ~0.7 GB · from huggingface.co/mradermacher
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/mradermacher/Zyte-1B-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Zyte-1B · needs ~0.7 GB · from huggingface.co/mradermacher
chat in the terminal
ollama run hf.co/mradermacher/Zyte-1B-GGUF:Q4_K_M

Other ways to run it

Run it as published · needs ~2.2 GB · from huggingface.co/venkycs (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='venkycs/Zyte-1B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/venkycs ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 97%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
EvalPlus / EvalPerf published evaluation runs	3	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%	Apache-2.0
prior · pull toward the middle		▇ 3%
weighted average		= 8.2

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-10-11 02:20 UTC · sources and licences · json