whatmodel.sh / Mistral-NeMo-Minitron 8B Instruct
Mistral-NeMo-Minitron 8B Instruct
↗ share
+ contribute
Mistral-NeMo-Minitron 8B Instruct is an open-weights language model from NVIDIA, released October 2024. Its published size is 8.41B parameters and a 8k-token context window. Licence: nvidia-open-model-license.
Catalogue identity notes
nvidia/Mistral-NeMo-Minitron-8B-Instruct @64261e0 (created 2024-10-02, licence nvidia-open-model-license). NVIDIA pruned/distilled 8B instruct model from Mistral NeMo 12B (Oct 2024). Independent rows: EuroEval English (life_in_the_uk).
Model information sources
Release date ↗ · Weights licence ↗
HF safetensors metadata 8,414,105,600 parameters.
$ how it compares
The LLMs ranked either side of Mistral-NeMo-Minitron 8B Instruct, out of 1132 with a score, then more from NVIDIA.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 560 |  Jamba 1.5 Large | 50±1 | local | ||
| 561 |  PLLuM-12B-nc-instruct (2507) | 50±4 | local | ||
| 562 | Mistral-NeMo-Minitron 8B Instruct | 50±8 | local | ||
| 563 |  Gemini 1.5 Flash (001) | 50±1 | comparison only | ||
| 564 | Jamba Large 1.7 | 50±15 | api price unknown +local | ||
| more from NVIDIA | |||||
| 109 | Nemotron 3 Ultra 550B-A55B | 69±1 | api $1.35/M +local | ||
| 182 | Nemotron Cascade 2 30B-A3B | 66±1 | local | ||
| 198 | Nemotron 3 Super 120B-A12B | 65±1 | api $0.28/M +local | ||
$ what it's good at
other tests1 not in a task · 69% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy | 83.1% ✎ | ▁▁▁▁▁▁▁▂▄█▄▃ beats 86/146 | 69% |
$ where to run it
llama.cpp · recommended
- 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 Mistral-NeMo-Minitron 8B Instruct · needs ~5.15 GB · from huggingface.co/bartowskichat in the terminal
llama cli -hf bartowski/Mistral-NeMo-Minitron-8B-Instruct-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/Mistral-NeMo-Minitron-8B-Instruct-GGUF:Q4_K_M
LM Studio
- Install LM Studio · Open the app once before using the lms command.
- Run Mistral-NeMo-Minitron 8B Instruct · needs ~5.15 GB · from huggingface.co/bartowski
- Or download it in the terminal
lms get https://huggingface.co/bartowski/Mistral-NeMo-Minitron-8B-Instruct-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 Mistral-NeMo-Minitron 8B Instruct · needs ~5.15 GB · from huggingface.co/bartowskichat in the terminal
ollama run hf.co/bartowski/Mistral-NeMo-Minitron-8B-Instruct-GGUF:Q4_K_M
Official weights and documentation: huggingface.co/nvidia ↗
$ how the score was worked out · EuroEval leaderboards (result… 69%
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 |
|---|---|---|
 EuroEval leaderboards (results collection), English generative leaderboard | 1 | 69% |
| prior · pull toward the middle | 31% | |
| weighted average | = 50.3 |
$ 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