Llama3 Ko 4bit is an open-source language model by vessl. Features: 8.2b LLM, VRAM: 5.8GB, Context: 8K, Quantized, Merged, LLM Explorer Score: 0.13.
Merged Model Arxiv:1910.09700 4-bit 4bit Bitsandbytes Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/vessl/llama3-ko-4bit
Llama3 Ko 4bit Benchmarks
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)
Llama3 Ko 4bit Parameters and Internals
| LLM Name | Llama3 Ko 4bit |
| Repository 🤗 | https://huggingface.co/vessl/llama3-ko-4bit |
| Merged Model | Yes |
| Model Size | 8.2b |
| Required VRAM | 5.8 GB |
| Updated | 2026-04-24 |
| Maintainer | vessl |
| Model Type | llama |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Llama3 Ko 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| KernelLLM Unsloth Bnb 4bit | 128K / 6 GB | 5 | 2 |
| Book 4bit | 8K / 5.8 GB | 6 | 0 |
| Ko Pt Model Test1 | 8K / 16.4 GB | 2027 | 0 |
| Maqa Llama 4bit | 8K / 5.8 GB | 13 | 0 |
| Llama SciQ 4bits | 8K / 5.8 GB | 5 | 0 |
| RAFT Llama3 Version 24.06.01 | 8K / 5.8 GB | 5 | 0 |
| Llama 3 Merged Linear | 8K / 5.8 GB | 93 | 0 |
| Llama 3 Ko Luxia Instruct | 8K / 16.4 GB | 13 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than vessl/llama3-ko-4bit .
Rank the Llama3 Ko 4bit 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? 53999 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