Athene-70B

+ contribute

Athene-70B is an open-weights language model from Nexusflow, released July 2024. Its published size is 70.6B parameters. Licence: nexusflow-research.

Catalogue identity notes

Comparison-only. Arena entry 'athene-70b-0725' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'athene-70b-0725' as 'Athene-70B' (NexusFlow, CC-BY-NC-4.0), linking https://huggingface.co/Nexusflow/Athene-70B. Maker repo Nexusflow/Athene-70B @4fd2cf3: licence tag other. 70,553,706,496 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-07: month the maker's Hugging Face repo was created (createdAt 2024-07-19). Card: 'Llama3-Athene-70B ... trained through RLHF based off Llama-3-70B-Instruct'; License: Nexusflow Research License. LMArena labels the key 'athene-70b-0725' as 'Athene-70B' linking Nexusflow/Athene-70B.

50.6±0.8#332 of 719 LLMsfrom 8 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Athene-70B, out of 828 with a score, then more from Nexusflow.

#	model	score	where	RAM	released
399	AceReason-Nemotron-1.0-14B NVIDIA	51±2	local	~10GB	2025-05
400	Llama-3-Instruct-8B-SimPO Princeton NLP	51±1	local	~6.6GB	2024-05
401	Athene-70B Nexusflow	51±1	local	~29GB	2024-07
402	Qwen2 72B Instruct Alibaba	51±1	local	~33GB	2024-06
403	Bielik 11B v2.0 Instruct SpeakLeash	51±3	local	~8.5GB	2024-08
	more from Nexusflow
290	Athene-V2-Chat 72B Nexusflow	56±2	local	~44GB	2024-11
626	Starling-LM 7B beta Nexusflow	40±1	local	~6GB	2024-03
753	NexusRaven V2 13B Nexusflow	29±3	local	~9.3GB	2023-12

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #297 of 458 * · 17% of its score · 1 test

Beats Solar Open 100B (102B-A12B), GLM-4.7-Flash, Qwen3-VL 30B-A3B Instruct here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, WizardLM 70B V1.0, Yi 1.5 9B Chat here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
CRUXEval (ZeroEval, 800 problems)	50.6% ✎	▁▂▆▃▆█▆▃▂·▁▁ beats 13/47	medium · avg 61%	▇▇▇▇▇▇▇ 17%	sharp · at its level

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #210 of 393 * · 23% of its score · 2 tests

Beats Granite 4.2 8B, Mistral Small 4 (119B-A6.5B), Gemma 2 9B IT SimPO here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, Granite 4.0 H Micro 3B, Gemma 3n E4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena-Hard (v0.1, GPT-4-1106 judge)	77.6% ✎	▂▁▁▅█▅▄▃▃▅▃▁ beats 48/60	medium · avg 52%	▇▇▇▇▇▇▇ 17%	sharp · at its level
LMArena (text)	1306.6 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 136/379	avg 1268	▇▇ 6.2%	blunt

math▁▂▃▅▆▅▄█▄▁▁▁ #326 of 398 * · 16% of its score · 2 tests

Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B, Tulu 2 DPO 13B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
MATH Level 5 (ZeroEval, 721 problems)	20.7% ✎	▁▁▁▆█▂▇▇▄··▂ beats 9/38	hard · avg 34%	▇▇▇▇ 8.8%	sharp · at its level
GSM8K (ZeroEval, zero-shot)	86.7% ✎	▁▄·▁▄█▅▅▅███ beats 18/43	very easy · avg 89%	▇▇▇ 6.8%	sharp

other tests3 not in a task · 44% of its score

test	result	vs the others in its run	difficulty	counts	why
MMLU-Redux (ZeroEval, 2,778 questions)	76.6% ✎	▁·▁▁▄▄▄▅█▄▂▁ beats 23/53	easy · avg 77%	▇▇▇▇▇▇▇▇▇▇▇ 27%	at its level
ZebraLogic (ZeroEval, 1,000 puzzles)	16.7% ✎	▁▁▃▆██▁▁·▁▁▁ beats 22/57	hard · avg 18%	▇▇▇▇ 10%	sharp
WildBench v2 WB-Score (task macro)	59.5374 WB-Score ✎	▁·▁▁·▃█▄▇▆▅▆ beats 52/52	avg 45.199 WB-Score	▇▇▇ 7.0%	sharp

$ 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 Athene-70B · needs ~42.52 GB · from huggingface.co/bartowski
chat in the terminal
llama cli -hf bartowski/Athene-70B-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/Athene-70B-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 Athene-70B · needs ~42.52 GB · from huggingface.co/bartowski
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/bartowski/Athene-70B-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 Athene-70B · needs ~42.52 GB · from huggingface.co/bartowski
chat in the terminal
ollama run hf.co/bartowski/Athene-70B-GGUF:Q4_K_M

Official weights and documentation: huggingface.co/Nexusflow ↗

$ how the score was worked out · WildEval ZeroEval published r… 69%, Arena-Hard-Auto v0.1 leaderbo… 17%, WildBench v2 leaderboard data… 7% and 1 more

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
WildEval ZeroEval published results	5	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 69%	Apache-2.0
Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)	1	▇▇▇▇▇ 17%	Apache-2.0
WildBench v2 leaderboard data (Ai2)	1	▇▇ 7%	Apache-2.0
LMArena leaderboard dataset	1	▇▇ 6%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 50.6

$ 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