Transcription Fixer Gemma 3 12B is an open-source language model by alecccdd. Features: 12b LLM, VRAM: 24.3GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.
Arxiv:1910.09700 4bit Base model:finetune:unsloth/ge... Base model:unsloth/gemma-3-12b... Conversational Dataset:alecccdd/transcription... De En Endpoints compatible Es Gemma3 Gemma3 text Quantized Region:us Safetensors Sharded Tensorflow Text-correction Unsloth
Model Card on HF 🤗: https://huggingface.co/alecccdd/transcription-fixer-gemma-3-12b
Transcription Fixer Gemma 3 12B 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)
Transcription Fixer Gemma 3 12B Parameters and Internals
| LLM Name | Transcription Fixer Gemma 3 12B |
| Repository 🤗 | https://huggingface.co/alecccdd/transcription-fixer-gemma-3-12b |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.3 GB |
| Updated | 2026-04-19 |
| Maintainer | alecccdd |
| Model Type | gemma3_text |
| Model Files | |
| Supported Languages | de en es |
| Quantization Type | 4bit |
| Model Architecture | Gemma3ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262208 |
| Torch Data Type | bfloat16 |
Best Alternatives to Transcription Fixer Gemma 3 12B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma 3 12B It Qat Abliterated | 128K / 47.2 GB | 124 | 12 |
| GrayLine Gemma3 12B | 128K / 24.3 GB | 160 | 2 |
| GaMS3 12B Instruct | 128K / 23.4 GB | 3410 | 2 |
| Typhoon2.1 Gemma3 12B | 128K / 23.4 GB | 12298 | 19 |
| YanoljaNEXT Rosetta 12B 2510 | 128K / 25.4 GB | 120 | 29 |
| Typhoon2.1 Gemma3 12B | 128K / 23.4 GB | 1610 | 18 |
| Gemma 3 12B It Abliterated V2 | 128K / 47.2 GB | 890 | 19 |
| Nile Chat 12B | 128K / 23.4 GB | 407 | 12 |
| Gemma 3 Coldbrew Test1 | 128K / 23.4 GB | 5 | 0 |
| Gemma 3 Glitter 12B | 128K / 23.4 GB | 139 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than alecccdd/transcription-fixer-gemma-3-12b .
Rank the Transcription Fixer Gemma 3 12B 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? 53053 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