LLM EXPLORER 58,975 MODELS INDEXED

Alloma 1B Instruct by uzlm

By uzlm · 31713 downloads
HF Repo ↗ Copy URL

Alloma 1B Instruct is an open-source language model by uzlm. Features: 1b LLM, VRAM: 2.5GB, Context: 128K, License: llama3.2, Instruction-Based, LLM Explorer Score: 0.26.

Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational Dataset:behbudiy/alpaca-cleane... Dataset:behbudiy/translation-i... Dataset:huggingfacefw/fineweb-...   Dataset:tahrirchi/uz-crawl   Dataset:tatsu-lab/alpaca Dataset:uazimov/uzbek-instruct...   Dataset:wikipedia   Dataset:yakhyo/uz-wiki   En   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Summarization   Tokenizer   Translation   Uz   Uzbek   Uzbekllm   Uzbeknlp
Model Card on HF 🤗: https://huggingface.co/uzlm/alloma-1B-Instruct 

Alloma 1B Instruct Parameters and Internals

LLM NameAlloma 1B Instruct
Repository 🤗https://huggingface.co/uzlm/alloma-1B-Instruct 
Base Model(s)  meta-llama/Llama-3.2-1B-Instruct   meta-llama/Llama-3.2-1B-Instruct
Model Size1b
Required VRAM2.5 GB
Updated2026-08-19
Maintaineruzlm
Model Typellama
Instruction-BasedYes
Model Files  2.5 GB
Supported Languagesuz en
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.52.1
Tokenizer ClassPreTrainedTokenizer
Padding Token<pad>
Vocabulary Size128257
Torch Data Typebfloat16

Best Alternatives to Alloma 1B Instruct

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
Llama3.2 1B Manumit V1128K / 2.5 GB1320
Llama 3.2 1B Instruct128K / 2.5 GB200
Llama 3.2 Mavrick.Spark 1B128K / 2.5 GB3102
...Claude Opus Fable5 V2 Thinking128K / 2.2 GB2884
Type O1 Mini Instruct128K / 2.5 GB2320
Note: green Score (e.g. "73.2") means that the model is better than uzlm/alloma-1B-Instruct.