LLM EXPLORER 59,420 MODELS INDEXED

Small Mistral 1 by ThorBaller

By ThorBaller · 5 downloads
HF Repo ↗ Copy URL

Small Mistral 1 is an open-source language model by ThorBaller. Features: 3.9b LLM, VRAM: 2.3GB, Context: 4K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  4-bit   4bit Base model:quantized:unsloth/p... Base model:unsloth/phi-3-mini-...   Bitsandbytes   Conversational   Dataset:qiaojin/pubmedqa   En   Endpoints compatible   Instruct   Mistral   Quantized   Region:us   Safetensors   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/ThorBaller/small_mistral_1 

Small Mistral 1 Parameters and Internals

Model Type 
text-generation-inference
Additional Notes 
The model was developed with Unsloth and the Huggingface TRL library.
Training Details 
Methodology:
Trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameSmall Mistral 1
Repository 🤗https://huggingface.co/ThorBaller/small_mistral_1 
Base Model(s)  ...hi 3 Mini 4K Instruct Bnb 4bit   unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Model Size3.9b
Required VRAM2.3 GB
Updated2026-05-19
MaintainerThorBaller
Model Typemistral
Instruction-BasedYes
Model Files  2.3 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Small Mistral 1

Best Alternatives
Context / RAM
Downloads
Likes
...hi 3 Mini 4K Instruct Bnb 4bit4K / 2.3 GB1697346
...3 Mini 4K Instruct V0 Bnb 4bit4K / 2.3 GB133
Phi 4K Gsm8k4K / 2.3 GB100
Phi 3 Autocomplete Search4K / 2.3 GB50
Hf4K / 2.3 GB120
MediChat Medium4K / 2.3 GB61
Recophi3 4bit4K / 2.3 GB60
Phi3 MeetingQA 4bit4K / 2.3 GB60
...Spydaz Web AI ChatQA 002 4 BIT512K / 4.1 GB240
Spydaz Web AI 02 4 BIT32K / 4.1 GB280
Note: green Score (e.g. "73.2") means that the model is better than ThorBaller/small_mistral_1.