Llama 3.2 4x3B Instruct is an open-source language model by noname0202. Features: 9.9b LLM, VRAM: 20GB, Context: 128K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.25.
Model Card on HF 🤗: https://huggingface.co/noname0202/Llama-3.2-4x3B-Instruct
Llama 3.2 4x3B Instruct Benchmarks
MMLU Pro: 25.39
GPQA: 3.02
MUSR: 4.42
BBH: 24.69
IFEval: 70.67 vs 88 (so35)-19.7%
MATH Lvl 5: 15.86
LLME Score: 0.24521
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 4x3B Instruct Parameters and Internals
| LLM Name | Llama 3.2 4x3B Instruct |
| Repository 🤗 | https://huggingface.co/noname0202/Llama-3.2-4x3B-Instruct |
| Model Size | 9.9b |
| Required VRAM | 20 GB |
| Updated | 2025-01-29 |
| Maintainer | noname0202 |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|begin_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Rank the Llama 3.2 4x3B 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