LLM EXPLORER 59,420 MODELS INDEXED

TinyMistral 248M V2 by Locutusque

By Locutusque · 1096 downloads

TinyMistral 248M V2 is an open-source language model by Locutusque. Features: 248m LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.16, Arc: 21.3, HellaSwag: 26.6, MMLU: 23.4.

  Dataset:locutusque/tm-data   Dataset:skylion007/openwebtext   En   Endpoints compatible   Mistral   Pytorch   Region:us   Safetensors

TinyMistral 248M V2 Parameters and Internals

Model Type 
text-generation
Supported Languages 
en (full)
Training Details 
Data Sources:
Skylion007/openwebtext, Locutusque/TM-DATA
Training Time:
500 GPU hours
Hardware Used:
single Titan V
LLM NameTinyMistral 248M V2
Repository πŸ€—https://huggingface.co/Locutusque/TinyMistral-248M-v2 
Model Size248m
Required VRAM1 GB
Updated2026-05-01
MaintainerLocutusque
Model Typemistral
Model Files  1.0 GB   1.0 GB
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32005
Torch Data Typefloat32

Best Alternatives to TinyMistral 248M V2

Best Alternatives
Context / RAM
Downloads
Likes
TinyMistral 248M V2.532K / 1 GB22627
TinyMistral 248M V2.5 Instruct32K / 1 GB211
...al V2.5 MiniPile Guidelines E132K / 0.6 GB132
TinyMistral V2 Test132K / 1 GB181
...adrin TinyMistral248M Instruct32K / 0.5 GB1087
TinyMistral 248M Instruct32K / 1 GB6912
TinyMistral 248M 8bits32K / 0.3 GB211
Tinymistv132K / 0.5 GB170
TinyMistral Haiku32K / 1 GB100
TinyMistral 248M V332K / 0.5 GB1978
Note: green Score (e.g. "73.2") means that the model is better than Locutusque/TinyMistral-248M-v2.