whatmodel.sh / Hermes 2 Theta Llama-3 70B

Hermes 2 Theta Llama-3 70B

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

Hermes 2 Theta Llama-3 70B is an open-weights language model from Nous Research, released June 2024. Its published size is 70.55B parameters and a 8k-token context window. Licence: llama3.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2024-06-20). Nous Research / Arcee AI merge on Llama 3 70B; exact checkpoint NousResearch/Hermes-2-Theta-Llama-3-70B. 70,553,706,496 parameters (safetensors metadata). GGUF size is the official Q4_K_M file (42.52 GB).

47.7±1.9#384 of 719 LLMsfrom 3 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Hermes 2 Theta Llama-3 70B, out of 828 with a score, then more from Nous Research.

#modelscorewhereRAMreleased
459GPT-4o mini Audio Preview (2024-12-17) OpenAI48±2comparison only2024-12
460Gemma 3n E4B Google48±1local~6.2GB2025-06
461Hermes 2 Theta Llama-3 70B Nous Research48±2local~47GB2024-06
462Granite 4.0 H Tiny (7B-A1B) IBM48±1local~5.6GB2025-09
463DeepSeek-Coder 7B Instruct v1.5 DeepSeek48±1local~5.9GB2024-01
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
498Hermes 2 Pro Llama 3 8B Nous Research46±3local~6.6GB2024-04

see all LLMs · find the ones that fit your machine

$ what it's good at

math▁▂▃▅▆▅▄█▄▁▁▁ #314 of 398 * · 67% of its score · 2 tests

Beats Athene-70B, OLMo 2 32B Instruct (0325) here, though they rank higher overall. Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B, Tulu 2 DPO 13B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MATH level 522.7% ✎▂▂▅▆▄█▆▃▅▂▃▄ beats 19/92hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 60%sharp
OTIS mock AIME 2024–20252.5% ✎▃▃▄▃▃▃▇▇█▃▂▅ beats 18/193very hard · avg 8.5%▇▇▇ 6.9%sharp · too hard for it · noisy
other tests1 not in a task · 32% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond37.5% ✎▁▁▁▁▂▄▆▄▅▇█▅ beats 32/208hard · avg 40%▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%sharp

$ where to run it

llama.cpp · recommended

  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 Theta Llama-3 70B · needs ~42.83 GB · from huggingface.co/NousResearch (official)
    chat in the terminal
    llama cli -hf NousResearch/Hermes-2-Theta-Llama-3-70B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf NousResearch/Hermes-2-Theta-Llama-3-70B-GGUF:Q4_K_M

LM Studio

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

    download it (macOS / Windows / Linux) ↗

  2. Run Hermes 2 Theta Llama-3 70B · needs ~42.83 GB · from huggingface.co/NousResearch (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-70B-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Hermes 2 Theta Llama-3 70B · needs ~42.83 GB · from huggingface.co/NousResearch (official)
    chat in the terminal
    ollama run hf.co/NousResearch/Hermes-2-Theta-Llama-3-70B-GGUF:Q4_K_M

Official weights and documentation: huggingface.co/NousResearch ↗

$ how the score was worked out · Epoch AI — internal evaluatio… 98%

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
Epoch AI — internal evaluations3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%CC BY 4.0
prior · pull toward the middle▇ 2%
weighted average= 47.7

$ 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