LLM EXPLORER 61,561 MODELS INDEXED

Llama3.2 3B INST Math1 by Alelcv27

By Alelcv27 · 8 downloads

Llama3.2 3B INST Math1 is an open-source language model by Alelcv27. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.24.

  4bit   Conversational   En   Endpoints compatible   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Unsloth

Llama3.2 3B INST Math1 Parameters and Internals

LLM NameLlama3.2 3B INST Math1
Repository πŸ€—https://huggingface.co/Alelcv27/Llama3.2-3B-INST-Math1 
Base Model(s)  unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit   unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
Model Size3b
Required VRAM6.5 GB
Updated2026-09-18
MaintainerAlelcv27
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Tokenizer ClassTokenizersBackend
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama3.2 3B INST Math1

Best Alternatives
Context / RAM
Downloads
Likes
Llama3 Finetuned Id 16bit128K / 6.5 GB6520
Slm Rag Sft Merged128K / 6.5 GB2970
Llama3.2 3B Legal Id Ft128K / 6.5 GB2640
...lama 3.2 3B Legal Assistant Id128K / 6.5 GB2830
Fine Tuning LLM128K / 6.5 GB5340
...Llama 3.2 3B Legal Chatbot Sft128K / 6.5 GB8170
Cheese 3B128K / 1.8 GB2491
Legal Llama3.2 3B Sft Id128K / 6.5 GB6800
...gabl Legal Chatbot Llama3.2 3B128K / 6.5 GB5280
Llama 3.2 3B Legal Id Sft128K / 6.5 GB2360
Note: green Score (e.g. "73.2") means that the model is better than Alelcv27/Llama3.2-3B-INST-Math1.