Darkit V2.5 Transformers is an open-source language model by darkps. Features: 14.8b LLM, VRAM: 29.5GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.29.
Base model:darkps/darkit-v2.5-... Base model:finetune:darkps/dar... Codegen Conversational Customizable Darkit-v2.5 Endpoints compatible Finetuned Multilingual Open-source Qwen3 Reasoning Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/darkps/darkit-v2.5-transformers
Darkit V2.5 Transformers 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)
Darkit V2.5 Transformers Parameters and Internals
| LLM Name | Darkit V2.5 Transformers |
| Repository 🤗 | https://huggingface.co/darkps/darkit-v2.5-transformers |
| Base Model(s) | |
| Model Size | 14.8b |
| Required VRAM | 29.5 GB |
| Updated | 2026-07-15 |
| Maintainer | darkps |
| Model Type | custom |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Darkit V2.5 Transformers
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Dhanishtha Nsfw | 40K / 29.5 GB | 733 | 21 |
| QiMing Janus Rhapsody | 40K / 29.2 GB | 40 | 0 |
| Dhanishtha 2.0 Preview 0825 | 40K / 29.5 GB | 31 | 19 |
| Merged16 Qwen Grpo 2 | 40K / 29.5 GB | 6 | 0 |
| Merged16 Qwen Grpo 3 | 40K / 29.5 GB | 6 | 0 |
Rank the Darkit V2.5 Transformers 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? 55114 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