Arxiv:2408.07990 Arxiv:2412.03187 Dataset:fuseai/fusechat-3.0-dp... Instruct Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/FuseAI/FuseChat-Llama-3.2-3B-Instruct
FuseChat Llama 3.2 3B Instruct Benchmarks
MMLU Pro: 23.68
GPQA: 6.15
MUSR: 7.69
BBH: 24.22
IFEval: 68.49 vs 88 (so35)-22.2%
MATH Lvl 5: 24.24
LLME Score: 0.29818
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)
FuseChat Llama 3.2 3B Instruct Parameters and Internals
| LLM Name | FuseChat Llama 3.2 3B Instruct |
| Repository 🤗 | https://huggingface.co/FuseAI/FuseChat-Llama-3.2-3B-Instruct |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-04-25 |
| Maintainer | FuseAI |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.4 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|eot_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to FuseChat Llama 3.2 3B Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1505928 | 1377 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 717 | 11 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 15 | 2 |
| Zeitgeist 3B V1 | 128K / 6.5 GB | 105 | 5 |
| ...lama 3.2 Rabbit Ko 3B Instruct | 128K / 6.5 GB | 2694 | 8 |
| Orpheus 3B 0.1 Pretrained | 128K / 6.6 GB | 3130 | 0 |
| ReasoningCore 3B T1 1 | 128K / 6.5 GB | 58 | 1 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 127219 | 61 |
| Llama 3.2 3B ToxicKod | 128K / 6.4 GB | 16 | 2 |
| ... 3.2 3B Math Instruct RE1 ORPO | 128K / 6.5 GB | 48 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than FuseAI/FuseChat-Llama-3.2-3B-Instruct .
Rank the FuseChat Llama 3.2 3B 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? 46678 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227