whatmodel.sh / Hermes 3 Llama 3.1 8B

Hermes 3 Llama 3.1 8B

+ contribute

Hermes 3 Llama 3.1 8B is an open-weights language model from Nous Research, released July 2024. Its published size is 8.03B parameters and a 128k-token context window. Licence: llama3.

Catalogue identity notes

Maker repo NousResearch/Hermes-3-Llama-3.1-8B @896ea44: licence tag llama3. 8,030,261,248 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2024-07: month the maker's Hugging Face repo was created (createdAt 2024-07-28). Ollama tags hermes3:8b-llama3.1-q4_K_M, hermes3:8b-llama3.1-q8_0 are the library's instruct/chat builds of this checkpoint (tag names on the pinned tags page); download sizes are estimated from the parameter count.

41.8±1.2#502 of 719 LLMsfrom 16 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Hermes 3 Llama 3.1 8B, out of 828 with a score, then more from Nous Research.

#	model	score	where	RAM	released
591	WizardLM 70B V1.0 Microsoft	42±1	local	~32GB	2023-08
592	WizardCoder Python 13B V1.0 WizardLM	42±2	local	~9.8GB	2023-08
593	Hermes 3 Llama 3.1 8B Nous Research	42±1	local	~6.6GB	2024-07
594	Falcon2 11B (base) TII	42±3	local	~8.2GB	2024-05
595	Granite 34B Code Base (8K) IBM	42±1	local	~24GB	2024-04
	more from Nous Research
389	Hermes 3 Llama 3.1 405B Nous Research	51±1	local	~114GB	2024-08
447	Hermes 3 Llama 3.1 70B Nous Research	49±1	local	~44GB	2024-07
461	Hermes 2 Theta Llama-3 70B Nous Research	48±2	local	~47GB	2024-06

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #357 of 458 * · 20% of its score · 1 test

Beats LFM2.5 8B-A1B, Qwen3-VL 2B Thinking, DeepSeek R1 Distill Qwen 7B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, Phi-3-mini-128k-instruct (Apr 2024), Code Tulu 2 13B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Aider code editing (133 Exercism Python exercises, two attempts)	30.1% ✎	▁·▁▃▄▁▆▄█▆▂▂ beats 2/62	medium · avg 54%	▇▇▇▇▇▇▇▇ 20%	at its level

chat & writing█········█·█ #3 of 3 * · 2.6% of its score · 1 test

test	result	vs the others in its run	difficulty	counts	why
IFEval (aggregation unspecified) lab	62.3% ✎	▁▁▃▃▂▄▄▆█▃▂▁ beats 23/141	easy · avg 79%	▇ 2.6%	at its level · small run

other tests14 not in a task · 77% of its score

test	result	vs the others in its run	difficulty	counts	why
BIG-Bench Hard lab	52.9% ✎	▁▁▁▁▂▄▅▅█▃▄▁ beats 55/129	medium · avg 72%	▇▇▇▇ 11%	sharp · at its level · small run
ARC Challenge lab	58.1% ✎	▆▁▁▂▂▅▇█▄▃▃▂ beats 70/97	medium · avg 73%	▇▇▇▇ 9.4%	sharp · at its level · small run
MMLU lab	64.8% ✎	▁▁▁▁▁▂▃▅█▃▆▃ beats 84/183	easy · avg 80%	▇▇▇ 8.0%	at its level · small run
WinoGrande lab	77.7% ✎	▁···▂▁▁▅█▇▃▁ beats 81/87	easy · avg 86%	▇▇▇ 6.9%	at its level · small run
GPQA (subset unspecified) lab	29.4% ✎	▂▁▂▂▄▃▆▃▅█▄▃ beats 17/104	hard · avg 41%	▇▇▇ 6.6%	sharp · small run
BoolQ lab	85.0% ✎	▁▄▅▆▂▆▄▄█▃▄▄ beats 51/58	easy · avg 90%	▇▇ 5.9%	at its level · small run
MMLU-Pro lab	32.1% ✎	▁▁·▁▁▃▃▂▄▅█▁ beats 15/188	medium · avg 52%	▇▇ 5.6%	at its level · small run
HellaSwag lab	82.8% ✎	▁▁▁▁▂▂▃▇█▆▅▃ beats 72/85	very easy · avg 89%	▇▇ 5.5%	small run

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Open Persian LLM Leaderboard v2 average (21 tasks)	50.4% ✎	▂▄▂▃█▄▃▆▃▅▂▂ beats 31/81	medium · avg 58%	▇▇ 5.2%	blunt · at its level
OpenBookQA lab	47.8% ✎	█▁▁▁▄▃▃▇▂▁▄▂ beats 41/65	medium · avg 55%	▇▇ 4.4%	small run
Open PT-LLM Leaderboard average (9 Portuguese tasks)	68.7% ✎	▃▁▁▁▁▁▁▁▂█▅▁ beats 154/276	medium · avg 73%	▇ 2.6%	at its level · noisy
MuSR lab	43.5% ✎	█······█···█ beats 0/2	medium · avg 53%	▇ 2.2%	blunt · at its level · small run
PIQA lab	80.3% ✎	▁▁▁▃▃▄▇█▄▃▁▁ beats 69/83	easy · avg 86%	▇ 2.0%	blunt · at its level · small run
TruthfulQA MC2 lab	58.7% ✎	█▅▇▅▁▄▃▇▅▄▁▁ beats 45/73	medium · avg 64%	▇ 1.0%	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 Hermes 3 Llama 3.1 8B · needs ~4.9 GB · from huggingface.co/bartowski
chat in the terminal
llama cli -hf bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/Hermes-3-Llama-3.1-8B-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 Hermes 3 Llama 3.1 8B · needs ~4.9 GB · from huggingface.co/bartowski
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/bartowski/Hermes-3-Llama-3.1-8B-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 Hermes 3 Llama 3.1 8B · needs ~5.32 GB · from ollama.com
chat in the terminal
ollama run hermes3:8b-llama3.1-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 Hermes 3 Llama 3.1 8B · needs ~8.5 GB, Mac only · from huggingface.co/Shaund91
chat in the terminal
mlx_lm.chat --model Shaund91/Hermes-3-Llama-3.1-8B-mlx-8Bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model Shaund91/Hermes-3-Llama-3.1-8B-mlx-8Bit

Official weights and documentation: huggingface.co/NousResearch ↗

$ how the score was worked out · Nous Research vendor-reported… 71%, Aider code editing benchmark… 20%, Open Persian LLM Leaderboard… 5% 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
Nous Research vendor-reported scores for its own Hermes models (Hermes 3 Technical Report) · lab-reported	13	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 71%	Factual vendor-reported score (not licensed content)
Aider code editing benchmark runs (old edit leaderboard)	1	▇▇▇▇▇▇ 20%	Apache-2.0
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)	1	▇▇ 5%	Apache-2.0
Open Portuguese LLM Leaderboard (archived)	1	▇ 3%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 41.8

$ 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