Merged Model Arxiv:2403.19522 Autotrain compatible Base model:cognitivecomputatio... Base model:nexesenex/llama 3.2... Base model:saisexperiments/evi... Conversational Endpoints compatible Llama Model-index Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Nexesenex/Llama_3.2_3b_Kermes_v2.1
Llama 3.2 3b Kermes V2.1 Benchmarks
MMLU Pro: 18.8
GPQA: 3.91
MUSR: 7.51
BBH: 22.17
IFEval: 55.84 vs 88 (so35)-36.5%
MATH Lvl 5: 5.21
LLME Score: 0.28448
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 3B Kermes V2.1 Parameters and Internals
| LLM Name | Llama 3.2 3b Kermes V2.1 |
| Repository 🤗 | https://huggingface.co/Nexesenex/Llama_3.2_3b_Kermes_v2.1 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 3b |
| Required VRAM | 6.4 GB |
| Updated | 2025-06-17 |
| Maintainer | Nexesenex |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | llama3.2 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Llama 3.2 3B Kermes V2.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ISA 03 Mini 3B Hybrid Preview | 256K / 6.5 GB | 1250 | 3 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1502135 | 1523 |
| Llama 3.2 3B | 128K / 6.5 GB | 265914 | 581 |
| Hermes 3 Llama 3.2 3B | 128K / 6.5 GB | 48671 | 161 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 1917 | 14 |
| Cogito V1 Preview Llama 3B | 128K / 7.2 GB | 2922 | 95 |
| Orpheus 3B 0.1 Ft | 128K / 6.6 GB | 27872 | 4 |
| Calme 3.1 Llamaloi 3B | 128K / 10.6 GB | 4284 | 1 |
| Llama 3.2 3B Bespoke Thought | 128K / 6.4 GB | 1475 | 3 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 206503 | 66 |
Note: green Score (e.g. "73.2") means that the model is better than Nexesenex/Llama_3.2_3b_Kermes_v2.1 .
Rank the Llama 3.2 3B Kermes V2.1 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? 48186 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124