whatmodel.sh / Hermes 2 Pro Llama 3 8B

Hermes 2 Pro Llama 3 8B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Hermes 2 Pro Llama 3 8B is an open-weights language model from Nous Research, released April 2024. Its published size is 8.03B parameters and a 8k-token context window. Licence: llama3.

Catalogue identity notes

Maker repo NousResearch/Hermes-2-Pro-Llama-3-8B @f798274: licence tag llama3. 8,030,523,392 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-30).

46.1±3.2#418 of 719 LLMsfrom 3 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Hermes 2 Pro Llama 3 8B, out of 828 with a score, then more from Nous Research.

#modelscorewhereRAMreleased
496Cogito v1 Preview Llama 3B Deep Cogito46±4local~3.4GB2025-03
497Code Llama 70B Instruct Meta46±1local~28GB2024-01
498Hermes 2 Pro Llama 3 8B Nous Research46±3local~6.6GB2024-04
499Llama 3 70B (base) Meta46±2local~43GB2024-04
500Granite 4.0 Micro 3B IBM46±1local~3.5GB2025-09
more from Nous Research
389Hermes 3 Llama 3.1 405B Nous Research51±1local~114GB2024-08
447Hermes 3 Llama 3.1 70B Nous Research49±1local~44GB2024-07
461Hermes 2 Theta Llama-3 70B Nous Research48±2local~47GB2024-06

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #267 of 300 * · 21% of its score · 1 test

Beats Magistral Small 1.0 (2506), Llama 4 Scout (109B-A17B), Bielik 11B v2.3 Instruct here, though they rank higher overall. Trails Qwen3 0.6B, Qwen2.5 1.5B Instruct, Granite 4.0 H 1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL v346.8% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 27/114medium · avg 52%▇▇▇▇▇▇▇▇ 21%blunt · at its level
other tests2 not in a task · 75% of its score
testresultvs the others in its rundifficultycountswhy
Polish EQ-Bench v2 (SpeakLeash)54.6% ✎▁··▁▁▂▂▆▅▆█▆ beats 29/70medium · avg 64%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)69.4% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 161/276medium · avg 73%▇▇▇▇▇▇▇▇ 21%at its level · noisy

$ where to run it

llama.cpp · recommended

version

  1. 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 ↗

  2. Run Hermes 2 Pro Llama 3 8B · needs ~4.9 GB · from huggingface.co/second-state
    chat in the terminal
    llama cli -hf second-state/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf second-state/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Hermes 2 Pro Llama 3 8B · needs ~4.9 GB · from huggingface.co/second-state

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Hermes 2 Pro Llama 3 8B · needs ~4.9 GB · from huggingface.co/second-state
    chat in the terminal
    ollama run hf.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~16.06 GB · from huggingface.co/NousResearch (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='NousResearch/Hermes-2-Pro-Llama-3-8B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/NousResearch ↗

$ how the score was worked out · SpeakLeash Polish EQ-Bench le… 54%, Open Portuguese LLM Leaderboa… 21%, Berkeley Function Calling Lea… 21%

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

sourceresultsshare of the scorelicence
SpeakLeash Polish EQ-Bench leaderboard1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇▇ 21%Apache-2.0
Berkeley Function Calling Leaderboard result archive1▇▇▇▇▇▇ 21%Apache-2.0
prior · pull toward the middle▇ 5%
weighted average= 46.1

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit 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 · sources and licences · json