LLM EXPLORER 60,783 MODELS INDEXED

Mistral NeMo Minitron 8B Base CODE Python by Agnuxo

By Agnuxo · 16 downloads
HF Repo ↗ Copy URL

Mistral NeMo Minitron 8B Base CODE Python is an open-source language model by Agnuxo. Features: 8b LLM, VRAM: 16.8GB, License: apache-2.0, LLM Explorer Score: 0.14.

  Arxiv:2604.19792   Adapter   Cajal   Code-generation-assistant   En   Es   Finetuned   Local-ai   Lora   Mistral   P2pclaw   Pytorch   Region:us   Safetensors   Scientific-research   Sharded
Model Card on HF 🤗: https://huggingface.co/Agnuxo/Mistral-NeMo-Minitron-8B-Base-CODE-Python 

Mistral NeMo Minitron 8B Base CODE Python Parameters and Internals

LLM NameMistral NeMo Minitron 8B Base CODE Python
Repository 🤗https://huggingface.co/Agnuxo/Mistral-NeMo-Minitron-8B-Base-CODE-Python 
Model Size8b
Required VRAM16.8 GB
Updated2026-09-09
MaintainerAgnuxo
Model Files  0.2 GB   4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   2.0 GB: 4-of-4
Supported Languagesen es
Model ArchitectureAdapter
Licenseapache-2.0
Model Max Length8192
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj|gate_proj|o_proj|down_proj|k_proj|up_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to Mistral NeMo Minitron 8B Base CODE Python

Best Alternatives
Context / RAM
Downloads
Likes
... 3 8B Instruct Bvr Finetune V38K / 16.1 GB50
...Max H3 Prompt Rewriter LoRA 8B0K / 2.8 GB13726
Qwen3 8B Text2sql Qlora0K / 0.2 GB411
Triage Qwen3 8B Lora0K / 0.2 GB131
...alized Harm V1 Qwen3 8B Seed430K / 0.2 GB101
Fovis0K / 0.1 GB391
Welles0K / 0 GB91
Drv Corrected Opd Qwen3 Vl 8B0K / 0.3 GB61
...eta Llama 3 8B Instruct Amazon0K / 0 GB60
Victor Triage Lora Llama3.1 8B0K / 0.1 GB70
Note: green Score (e.g. "73.2") means that the model is better than Agnuxo/Mistral-NeMo-Minitron-8B-Base-CODE-Python.