whatmodel.sh / Nous Hermes 2 Yi 34B
Nous Hermes 2 Yi 34B
↗ share
+ contribute
Nous Hermes 2 Yi 34B is an open-weights language model from Nous Research, released December 2023. Its published size is 34.39B parameters and a 4k-token context window. Licence: apache-2.0.
Catalogue identity notes
NousResearch/Nous-Hermes-2-Yi-34B @fcb0a88 (created 2023-12-23, licence apache-2.0). Independent row: Open PT-LLM (Portuguese) leaderboard average.
Model information sources
Release date ↗ · Weights licence ↗
HF safetensors metadata 34,388,917,248 parameters.
$ how it compares
The LLMs ranked either side of Nous Hermes 2 Yi 34B, out of 1132 with a score, then more from Nous Research.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 583 |  Codestral 22B v0.1 | 50±1 | local | ||
| 584 |  HuatuoGPT-o1-7B | 50±4 | local | ||
| 585 | Nous Hermes 2 Yi 34B | 50±7 | local | ||
| 586 |  GLM-4 (0116) | 50±1 | comparison only | ||
| 587 |  Llama 3 70B Instruct | 50±0 | local | ||
| more from Nous Research | |||||
| 534 | Hermes 3 Llama 3.1 405B | 51±1 | local | ||
| 624 | Hermes 3 Llama 3.1 70B | 49±1 | local | ||
| 641 | Hermes 2 Theta Llama-3 70B | 48±2 | local | ||
$ what it's good at
other tests1 not in a task · 81% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 72.4% ✎ | ▃▁▁▁▁▁▁▁▂█▅▁ beats 196/276 | 81% |
$ 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 | shWindowsirm https://llama.app/install.ps1 | iex - Run Nous Hermes 2 Yi 34B · needs ~20.7 GB · from huggingface.co/TheBlokechat in the terminal
llama cli -hf TheBloke/Nous-Hermes-2-Yi-34B-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf TheBloke/Nous-Hermes-2-Yi-34B-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Nous Hermes 2 Yi 34B · needs ~20.7 GB · from huggingface.co/TheBloke
- Or download it in the terminal
lms get https://huggingface.co/TheBloke/Nous-Hermes-2-Yi-34B-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Nous Hermes 2 Yi 34B · needs ~19 GB · from ollama.comchat in the terminal
ollama run nous-hermes2:34b
MLX (Mac)
version
- Install MLX (Mac) · Apple silicon Macs only, text only.with uv
uv tool install mlx-lmorpip install mlx-lm - Run Nous Hermes 2 Yi 34B · needs ~19.3 GB, Mac only · from huggingface.co/tstepspamchat in the terminal
mlx_lm.chat --model tstepspam/Nous-Hermes-2-Yi-34B-Q4-MLX - Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model tstepspam/Nous-Hermes-2-Yi-34B-Q4-MLX
Official weights and documentation: huggingface.co/NousResearch ↗
$ how the score was worked out · Open Portuguese LLM Leaderboa… 81%
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 |
|---|---|---|
 Open Portuguese LLM Leaderboard (archived) | 1 | 81% |
| prior · pull toward the middle | 19% | |
| weighted average | = 49.7 |
$ improve this page
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