LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

TinyMistral 248M Instruct by Locutusque

 »  All LLMs  »  Locutusque  »  TinyMistral 248M Instruct   URL Share it on

  851   

TinyMistral 248M Instruct is an open-source language model by Locutusque. Features: 248m LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.16, Arc: 24.3, HellaSwag: 27.5, MMLU: 25.2.

Base model:finetune:locutusque... Base model:locutusque/tinymist...   Dataset:berkeley-nest/nectar Dataset:locutusque/instructmix...   En   Endpoints compatible   Instruct   Mistral   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Locutusque/TinyMistral-248M-Instruct 

TinyMistral 248M Instruct Benchmarks

ARC: 24.32 vs 96.7 (so35)-74.9%
HellaSwag: 27.52 vs 95.3 (gpt4)-71.1%
MMLU: 25.18 vs 88.3 (so35)-71.5%
LLME Score: 0.16118
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TinyMistral 248M Instruct (Locutusque/TinyMistral-248M-Instruct)
🌟 Advertise your project 🚀

TinyMistral 248M Instruct Parameters and Internals

Model Type 
text-generation
Additional Notes 
During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset. It has so far been trained on approximately 608,000 examples. More epochs are planned for this model.
Supported Languages 
en ()
Training Details 
Data Sources:
Locutusque/InstructMixCleaned, berkeley-nest/Nectar
Methodology:
Fully fine-tuned on Locutusque/InstructMix.
LLM NameTinyMistral 248M Instruct
Repository 🤗https://huggingface.co/Locutusque/TinyMistral-248M-Instruct 
Base Model(s)  TinyMistral 248M   Locutusque/TinyMistral-248M
Model Size248m
Required VRAM1 GB
Updated2026-05-14
MaintainerLocutusque
Model Typemistral
Instruction-BasedYes
Model Files  1.0 GB   1.0 GB
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.1
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32005
Torch Data Typefloat32

Quantized Models of the TinyMistral 248M Instruct

Model
Likes
Downloads
VRAM
Tinymistralredq0380 GB
Tinymistralredq000 GB

Best Alternatives to TinyMistral 248M Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...adrin TinyMistral248M Instruct32K / 0.5 GB21277
TinyMistral 248M V2.5 Instruct32K / 1 GB211
Tinymistv132K / 0.5 GB170
...istral 248M V2.5 Instruct Orpo32K / 0.5 GB80
TinyMistral 248M V2 Instruct32K / 0.5 GB8247
...stral V2 Pycoder Instruct 248M32K / 1 GB153
...mistral 248M Hypnosis Instruct32K / 0.5 GB92
...al V2 Pycoder Instruct 248M V132K / 0.5 GB111
...istral Magicoder Instruct 248M32K / 0.5 GB222
Tinymistv132K / 0.5 GB00
Note: green Score (e.g. "73.2") means that the model is better than Locutusque/TinyMistral-248M-Instruct.

Rank the TinyMistral 248M Instruct Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer