LLM EXPLORER 59,358 MODELS INDEXED

Llama 3.2 1B Instruct Sum KTO 1K 1 2ep by Muadil

By Muadil · 8 downloads
HF Repo ↗ Copy URL

Llama 3.2 1B Instruct Sum KTO 1K 1 2ep is an open-source language model by Muadil. Features: 1b LLM, VRAM: 2.5GB, Context: 128K, Instruction-Based, LLM Explorer Score: 0.16.

  Arxiv:1910.09700   Conversational   Endpoints compatible   Instruct   Llama   Llama-factory   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Muadil/Llama-3.2-1B-Instruct_sum_KTO_1k_1_2ep 

Llama 3.2 1B Instruct Sum KTO 1K 1 2ep Parameters and Internals

LLM NameLlama 3.2 1B Instruct Sum KTO 1k 1 2ep
Repository 🤗https://huggingface.co/Muadil/Llama-3.2-1B-Instruct_sum_KTO_1k_1_2ep 
Model Size1b
Required VRAM2.5 GB
Updated2026-08-02
MaintainerMuadil
Model Typellama
Instruction-BasedYes
Model Files  2.0 GB: 1-of-2   0.5 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3.2 1B Instruct Sum KTO 1K 1 2ep

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 1B Instruct128K / 2.5 GB212072100
...1B Claude Opus Fable5 Thinking128K / 2.2 GB6165166
Llama 3.2 1B Instruct128K / 2.5 GB101146341549
LlaMa3.2 1B Instruct128K / 4.9 GB140
Llama 3.2 1B Instruct Bf16128K / 2.5 GB5105
Llama 3.2 1B Instruct128K / 2.5 GB200
Llama3.2 1B Manumit V1128K / 2.5 GB1320
...Claude Opus Fable5 V2 Thinking128K / 2.2 GB2884
Llama 3.2 Mavrick.Spark 1B128K / 2.5 GB2602
Type O1 Mini Instruct128K / 2.5 GB2320
Note: green Score (e.g. "73.2") means that the model is better than Muadil/Llama-3.2-1B-Instruct_sum_KTO_1k_1_2ep.