whatmodel.sh / OpenLLaMA 7B v2

OpenLLaMA 7B v2

+ contribute

OpenLLaMA 7B v2 is an open-weights language model from OpenLM Research, released July 2023. Licence: apache-2.0.

Catalogue identity notes

Maker repo openlm-research/open_llama_7b_v2 @e5961de: licence tag apache-2.0. Released 2023-07: month the maker's Hugging Face repo was created (createdAt 2023-07-06). Pretrained base checkpoint (not an instruct/chat version).

28.9±0.9#649 of 719 LLMsfrom 12 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of OpenLLaMA 7B v2, out of 828 with a score, then more from OpenLM Research.

#	model	score	where	RAM	released
746	StableLM-3B-4E1T Stability AI	29±1	local	~3.3GB	2023-09
747	Gemma 2B (base) Google	29±1	local	~3.2GB	2024-02
748	OpenLLaMA 7B v2 OpenLM Research	29±1	local	~9.1GB	2023-07
749	Gemma 1.1 2B IT Google	29±1	local	~3.2GB	2024-04
750	StableLM-Base-Alpha 7B v2 Stability AI	29±1	local	~30GB	2023-08
	more from OpenLM Research
781	OpenLLaMA 3B v2 OpenLM Research	25±1	local	~4.2GB	2023-07

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests12 not in a task · 100% of its score

test	result	vs the others in its run	difficulty	counts	why
ARC Challenge	42.4% ✎	▁·▁··▁▁▇▂█▆▃ beats 17/26	easy · avg 85%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%	sharp
WinoGrande	65.8% ✎	▁····▁··▁▂█▄ beats 13/26	easy · avg 89%	▇▇▇▇▇ 12%	at its level
BoolQ	71.4% ✎	▂▃▂▅▆▂▅▆█▂▂▂ beats 15/26	easy · avg 91%	▇▇▇▇ 10%	at its level
ARC Easy	69.7% ✎	▁▁·▁▁▄▅▄█▅▁▃ beats 18/26	easy · avg 88%	▇▇▇ 6.9%	at its level
HellaSwag	74.6% ✎	▃···▁▇▅█▇▃▁▁ beats 18/26	very easy · avg 92%	▇▇ 5.6%	at its level
SciQ	93.8% ✎	▁·▁·▁·▃▅▃█▄▁ beats 19/26	very easy · avg 98%	▇▇ 5.4%	typical
PIQA	79.2% ✎	▁·▁··▁▁▃█▅█▂ beats 23/26	easy · avg 88%	▇▇ 4.4%	blunt · at its level
OpenBookQA	30.2% ✎	█·▁▁▃·▁▃▅▇▃▄ beats 14/26	medium · avg 53%	▇ 3.5%	too hard for it

4 more tests

test	result	vs the others in its run	difficulty	counts	why
LAMBADA (OpenAI version), last-word accuracy	71.0% ✎	▁··▂▁▁▁▂▆█▅▃ beats 18/26	very easy · avg 89%	▇ 2.6%	blunt · at its level
Social IQA	42.0% ✎	▁···▁▃█▁▁▁·▁ beats 10/26	medium · avg 59%	▇ 2.5%	blunt
Open PT-LLM Leaderboard average (9 Portuguese tasks)	39.2% ✎	▃▁▁▁▁▃▁▁▂█▅▁ beats 47/276	medium · avg 73%	▇ 1.1%	noisy
TruthfulQA MC2	34.6% ✎	█·█·█▄···▄·█ beats 2/9	medium · avg 61%	▇ 0.5%	blunt · at its level

$ where to run it

llama.cpp · recommended

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 OpenLLaMA 7B v2 · needs ~7.2 GB · from huggingface.co/exocet25
chat in the terminal
llama cli -hf exocet25/open_llama_7b_v2-Q8_0-GGUF:q8_0
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf exocet25/open_llama_7b_v2-Q8_0-GGUF:q8_0

LM Studio

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run OpenLLaMA 7B v2 · needs ~7.2 GB · from huggingface.co/exocet25
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/exocet25/open_llama_7b_v2-Q8_0-GGUF@q8_0 -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run OpenLLaMA 7B v2 · needs ~7.2 GB · from huggingface.co/exocet25
chat in the terminal
ollama run hf.co/exocet25/open_llama_7b_v2-Q8_0-GGUF:q8_0

Other ways to run it

Run it as published · needs ~13.48 GB · from huggingface.co/openlm-research (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='openlm-research/open_llama_7b_v2', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/openlm-research ↗

$ how the score was worked out · Stability AI — original Stabl… 98%, Open Portuguese LLM Leaderboa… 1%

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
Stability AI — original StableLM zero-shot evaluation outputs	11	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%	Apache-2.0
Open Portuguese LLM Leaderboard (archived)	1	▇ 1%	Apache-2.0
prior · pull toward the middle		▇ 0%
weighted average		= 28.9

$ 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