Model Card on HF 🤗: https://huggingface.co/NTIS/hf_gemma3_21-checkpoint-128000
Hf Gemma3 21 Checkpoint 128000 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)
Hf Gemma3 21 Checkpoint 128000 Parameters and Internals
| LLM Name | Hf Gemma3 21 Checkpoint 128000 |
| Repository 🤗 | https://huggingface.co/NTIS/hf_gemma3_21-checkpoint-128000 |
| Model Size | 999.9m |
| Required VRAM | 4 GB |
| Updated | 2025-07-02 |
| Maintainer | NTIS |
| Model Type | gemma3_text |
| Model Files | |
| Supported Languages | ko en |
| Model Architecture | Gemma3ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262144 |
| Torch Data Type | float32 |
Best Alternatives to Hf Gemma3 21 Checkpoint 128000
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Uwes Med Model | 32K / 4 GB | 1742 | 0 |
| Sam Reason S2.1 | 32K / 2 GB | 56 | 3 |
| Sam Reason S2 | 32K / 2 GB | 19 | 1 |
| Gemma 3 Sft Peft | 32K / 5.2 GB | 27 | 0 |
| Sft Unsafe Model Full | 32K / 4 GB | 9 | 0 |
| Sft Model State Dict Full | 32K / 4 GB | 7 | 0 |
| ...e Merged Model State Dict Peft | 32K / 4 GB | 7 | 0 |
| Sft Model State Dict Peft | 32K / 4 GB | 7 | 0 |
| Gemma 3 Sft | 32K / 4 GB | 11 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than NTIS/hf_gemma3_21-checkpoint-128000 .
Rank the Hf Gemma3 21 Checkpoint 128000 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? 49328 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124