Gemma4 26B Atc Finetune 32 64 V2 Merged 16bit is an open-source language model by xl-24. Features: 26b LLM, VRAM: 51.6GB, License: apache-2.0, Quantized, Fine-Tuned, Merged, LLM Explorer Score: 0.44, ELO: 1438.
| LLM Name | Gemma4 26B Atc Finetune 32 64 V2 Merged 16bit |
| Repository π€ | https://huggingface.co/xl-24/gemma4-26b-atc-finetune-32-64-v2-merged-16bit |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 26b |
| Required VRAM | 51.6 GB |
| Updated | 2026-11-21 |
| Maintainer | xl-24 |
| Model Type | gemma4 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 16bit |
| Model Architecture | Gemma4ForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Transformers Version | 5.17.0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| OTel 2.0 Decision 26B A4B 4bit | 0K / 17.3 GB | 914755 | 4 |
| ...6B A4B It Qat Q4 0 Unquantized | 0K / 51.6 GB | 33696 | 50 |
| Gemma 4 26B A4b It 4bit | 0K / 15.4 GB | 27543 | 79 |
| ...yberSecurity 26B A4B V2 Q8 MLX | 0K / 40.6 GB | 393 | 1 |
| ...yberSecurity 26B A4B V2 Q4 MLX | 0K / 35.4 GB | 246 | 1 |
| ...6B A4B It Qat Q4 0 Unquantized | 0K / 51.6 GB | 3487 | 3 |
| Gemma 4 26B A4b It 8bit | 0K / 27.9 GB | 2917 | 14 |
| OTel 2.0 Decision 26B A4B 4bit | 0K / 17.3 GB | 63 | 1 |
| Gemma 4 26B A4b It UD MLX 4bit | 0K / 16.2 GB | 1527 | 34 |
| Gemma 4 26B A4b It MLX 8bit | 0K / 27.9 GB | 936 | 16 |