Llama 3.2 SUN 1B Instruct is an open-source language model by meditsolutions. Features: 1b LLM, VRAM: 1.6GB, Context: 128K, License: llama3.2, Quantized, Instruction-Based, LLM Explorer Score: 0.34, ELO: 1322.
Base model:meta-llama/llama-3.... Base model:quantized:meta-llam... Conversational Dataset:allenai/llama-3.1-tulu... Dataset:allenai/tulu-3-sft-mix... Dataset:argilla/capybara-prefe... Dataset:argilla/magpie-ultra-v... Dataset:argilla/openhermespref... Dataset:huggingfacetb/everyday... Dataset:mlabonne/open-perfectb... Dataset:prolificai/social-reas... Dataset:wizardlmteam/wizardlm ... En Endpoints compatible Gguf Instruct Llama Model-index Q8 Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/meditsolutions/Llama-3.2-SUN-1B-Instruct
Llama 3.2 SUN 1B Instruct Benchmarks
LMSys ELO: 1322 vs 1272 (so35)3.9%
MMLU Pro: 8.68
MUSR: 4.05
BBH: 9.18
IFEval: 64.13 vs 88 (so35)-27.1%
MATH Lvl 5: 7.1
LLME Score: 0.34365
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Llama 3.2 SUN 1B Instruct Parameters and Internals
| LLM Name | Llama 3.2 SUN 1B Instruct |
| Repository 🤗 | https://huggingface.co/meditsolutions/Llama-3.2-SUN-1B-Instruct |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 1.6 GB |
| Updated | 2026-04-05 |
| Maintainer | meditsolutions |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | q8|gguf |
| Model Architecture | LlamaMedITForCausalLM |
| License | llama3.2 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Rank the Llama 3.2 SUN 1B Instruct Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a