Base model:adapter:google/gemm... Base model:google/gemma-3-4b-i... Conversational Lora Peft Region:us Safetensors Sft Trl
Model Card on HF 🤗: https://huggingface.co/Reubencf/gemma3-konkani
Gemma3 Konkani 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)
Gemma3 Konkani Parameters and Internals
| LLM Name | Gemma3 Konkani |
| Repository 🤗 | https://huggingface.co/Reubencf/gemma3-konkani |
| Model Name | gemma3-konkani |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 0 GB |
| Updated | 2025-08-23 |
| Maintainer | Reubencf |
| Model Files | |
| Model Architecture | AutoModel |
| Is Biased | none |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <eos> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|v_proj|o_proj|q_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.1 |
| R Param | 16 |
Best Alternatives to Gemma3 Konkani
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| AYA Mistral7B Instruct TR 4B | 0K / 0.3 GB | 0 | 6 |
| Basically Human 4B F32 GGUF | 0K / 1.7 GB | 125 | 2 |
| II Search 4B GGUF | 0K / 1.7 GB | 1622 | 5 |
| Qwen3 4B Abliterated F32 GGUFs | 0K / 1.7 GB | 1533 | 2 |
| Chinda Qwen3 4B F32 GGUF | 0K / 1.7 GB | 59 | 2 |
| Calme 2.3 Phi3 4B GGUF | 0K / 1.4 GB | 79 | 5 |
| Calme 2.2 Phi3 4B GGUF | 0K / 1.4 GB | 54 | 2 |
| Calme 2.1 Phi3 4B GGUF | 0K / 1.4 GB | 20 | 1 |
Rank the Gemma3 Konkani 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? 50836 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124