whatmodel.sh / Llama 3.1 Tulu 3 70B

Llama 3.1 Tulu 3 70B

+ contribute

Llama 3.1 Tulu 3 70B is an open-weights language model from Ai2, released November 2024. Its published size is 70.6B parameters and a 131k-token context window. Licence: llama3.1.

Catalogue identity notes

Arena entry 'llama-3.1-tulu-3-70b' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'llama-3.1-tulu-3-70b' as 'Llama-3.1-Tulu-3-70B' (Ai2, Llama 3.1), linking https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B. Maker repo allenai/Llama-3.1-Tulu-3-70B @cfc1d85: licence tag llama3.1. 70,553,837,568 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-11: month the maker's Hugging Face repo was created (createdAt 2024-11-20).

53.6±1.4#289 of 719 LLMsfrom 10 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Llama 3.1 Tulu 3 70B, out of 828 with a score, then more from Ai2.

#	model	score	where	RAM	released
344	GPT-4 Turbo Preview (0125) OpenAI	54±1	comparison only		2024-01
345	Claude 3.5 Haiku Anthropic	54±1	comparison only		2024-10
346	Llama 3.1 Tulu 3 70B Ai2	54±1	local	~43GB	2024-11
347	DeepSeek-V2.5 DeepSeek	54±1	local	~151GB	2024-09
348	DeepSeek-V2 Chat (0628) DeepSeek	54±1	local	~66GB	2024-07
	more from Ai2
259	Olmo 3.1 32B Think Ai2	58±1	local	~21GB	2025-12
262	Olmo 3 32B Think Ai2	58±1	local	~21GB	2025-11
314	Molmo 2 8B Ai2	55±2	local	~6.8GB	2025-12

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #239 of 393 · 32% of its score · 3 tests

Beats Mistral Small 4 (119B-A6.5B), Ministral 3 14B Reasoning 2512, Qwen2.5 Coder 32B Instruct here, though they rank higher overall. Trails Flan-T5 XXL, Granite 4.0 H 1B, LFM2.5 1.2B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LMArena (text)	1286.1 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 113/379	avg 1268	▇▇▇▇▇▇▇ 18%	blunt
AlpacaEval 2 length-controlled lab	49.8% ✎	▁▁▃▄▆██▆▃▃▁▁ beats 128/155	medium · avg 47%	▇▇▇▇ 8.9%	at its level · small run
IFEval prompt-level loose lab	83.2% ✎	▁▂▁▂▁▃▁▂█▂▂▁ beats 18/25	easy · avg 79%	▇▇ 4.6%	small run

math▁▂▃▅▆▅▄█▄▁▁▁ #241 of 398 * · 21% of its score · 2 tests

Beats Command A (03-2025), GPT-4o (2024-11-20), GPT-4 Turbo (2024-04-09) here, though they rank higher overall. Trails DeepSeek R1 Distill Qwen 1.5B, Tulu 2 DPO 70B, OpenThinker 7B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
MATH (subset unspecified) lab	63.0% ✎	▂▄▄▃█▇▅▆▄▃▄▁ beats 37/80	medium · avg 58%	▇▇▇▇ 11%	at its level · small run
GSM8K lab	93.5% ✎	▂▂▂▅▅▆▅▇█▇▄▃ beats 135/146	very easy · avg 87%	▇▇▇▇ 10%	sharp · small run

other tests5 not in a task · 46% of its score

test	result	vs the others in its run	difficulty	counts	why
BIG-Bench Hard lab	85.0% ✎	▁▁▁▁▂▄▅▅█▃▄▁ beats 119/129	easy · avg 77%	▇▇▇▇▇▇ 16%	sharp · small run
DROP lab	74.3% ✎	▅··▅·█▅█▅▃▃▅ beats 11/17	easy · avg 65%	▇▇▇▇▇ 14%	at its level · small run
MMLU lab	83.1% ✎	▁▁▁▁▁▂▃▅█▃▆▃ beats 147/183	easy · avg 79%	▇▇▇▇ 11%	small run
PopQA lab	46.5% ✎	▁▁▂▃▅▃▂█▂▃·▄ beats 34/36	hard · avg 35%	▇▇ 4.1%	blunt · at its level · small run
TruthfulQA MC2 lab	67.6% ✎	█▅▇▅▁▄▁▇▅▄▁▁ beats 63/73	medium · avg 64%	▇ 1.5%	blunt · at its level · small run

$ 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 Llama 3.1 Tulu 3 70B · needs ~42.5 GB · from huggingface.co/lmstudio-community
chat in the terminal
llama cli -hf lmstudio-community/Llama-3.1-Tulu-3-70B-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf lmstudio-community/Llama-3.1-Tulu-3-70B-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 Llama 3.1 Tulu 3 70B · needs ~42.5 GB · from huggingface.co/lmstudio-community
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/lmstudio-community/Llama-3.1-Tulu-3-70B-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 Llama 3.1 Tulu 3 70B · needs ~42.86 GB · from ollama.com
chat in the terminal
ollama run tulu3:70b-q4_K_M

MLX (Mac)

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run Llama 3.1 Tulu 3 70B · needs ~39.7 GB, Mac only · from huggingface.co/mlx-community
chat in the terminal
mlx_lm.chat --model mlx-community/Llama-3.1-Tulu-3-70B-4bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/Llama-3.1-Tulu-3-70B-4bit

Weights and documentation: huggingface.co/allenai ↗

$ how the score was worked out · Tülu 3: Pushing Frontiers in… 81%, LMArena leaderboard dataset 18%

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
Tülu 3: Pushing Frontiers in Open Language Model Post-Training (Lambert et al., Ai2) · lab-reported	9	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%	CC BY 4.0
LMArena leaderboard dataset	1	▇▇▇▇▇▇ 18%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 53.6

$ 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