# Mistral NeMo Minitron 8B

Mistral NeMo Minitron 8B is an AI model released by NVIDIA on Aug 21 2024. It has 8B parameters, an 8k context window and open weight.

## Facts

| Field | Value |
| --- | --- |
| Model | Mistral NeMo Minitron 8B |
| Developer | NVIDIA |
| Release date | Wednesday, Aug 21 2024 |
| Licensing | Open Weight |
| Parameters | 8B |
| Context window | 8k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| HumanEval | 36.22% | Lab | 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. |
| ARC-Challenge | 64.42% | Lab | multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI |
| HellaSwag | 83.03% | Lab | commonsense completion of short scenarios |
| WinoGrande | 80.35% | Lab | resolving ambiguous pronouns in context |
| MMLU | 69.51% | Lab | A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. |
| GSM8K | 58.45% | Lab | Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. |

## About Mistral NeMo Minitron 8B

NVIDIA released Mistral NeMo Minitron 8B on August 21, 2024. Mistral AI and NVIDIA jointly developed the original 12B Mistral NeMo. NVIDIA pruned that model to 8B parameters and trained the smaller model using knowledge distillation.

The 8B base checkpoint targeted workloads that could run on a workstation. NVIDIA tested it on language understanding, math and code generation and reported 69.51% on MMLU.

## Questions and answers

### When was Mistral NeMo Minitron 8B released?

Mistral NeMo Minitron 8B was released by NVIDIA on Wednesday, Aug 21 2024.

### Who made Mistral NeMo Minitron 8B?

Mistral NeMo Minitron 8B was built by NVIDIA. The dominant AI chipmaker, publishing the open Nemotron model family. Ships weights, datasets and training recipes to seed demand for its hardware rather than to sell a chatbot.

### What benchmark scores did Mistral NeMo Minitron 8B get?

Mistral NeMo Minitron 8B reports 6 tracked benchmark scores — HumanEval: 36.22%; ARC-Challenge: 64.42%; HellaSwag: 83.03%; WinoGrande: 80.35%; MMLU: 69.51%; GSM8K: 58.45%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Mistral NeMo Minitron 8B?

Mistral NeMo Minitron 8B has a context window of 8k. Providers may specify separate input and output token limits.

### How many parameters does Mistral NeMo Minitron 8B have?

Mistral NeMo Minitron 8B is reported at 8B parameters.

### Is Mistral NeMo Minitron 8B open source?

Partly. Mistral NeMo Minitron 8B is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after Mistral NeMo Minitron 8B?

NVIDIA's previous tracked release was Nemotron-4 340B on Jun 14 2024, 68 days earlier. It was followed by Llama 3.1 Nemotron 51B on Sep 23 2024.


---

Canonical page: https://aireleasetracker.com/model/nvidia/mistral-nemo-minitron-8b
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
