Model Card on HF 🤗: https://huggingface.co/HLeiTR/qwen3_14b_full_15k_ckpt_125
Qwen3 14b Full 15k Ckpt 125 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)
Qwen3 14B Full 15K Ckpt 125 Parameters and Internals
| LLM Name | Qwen3 14b Full 15k Ckpt 125 |
| Repository 🤗 | https://huggingface.co/HLeiTR/qwen3_14b_full_15k_ckpt_125 |
| Model Size | 14b |
| Required VRAM | 29.5 GB |
| Updated | 2025-07-23 |
| Maintainer | HLeiTR |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen3 14B Full 15K Ckpt 125
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 14B | 40K / 29.7 GB | 782578 | 213 |
| Qwen3 14B FP8 | 40K / 16.4 GB | 17622 | 26 |
| Dhanishtha 2.0 Preview | 40K / 29.5 GB | 492 | 54 |
| Qwen3 14B | 40K / 29.5 GB | 12332 | 10 |
| Qwen3 14B Abliterated | 40K / 29.5 GB | 1682 | 38 |
| GrayLine Qwen3 14B | 40K / 29.5 GB | 944 | 24 |
| Smoothie Qwen3 14B | 40K / 29.5 GB | 2299 | 5 |
| ...Omega Directive Qwen3 14B V1.1 | 40K / 29.5 GB | 1001 | 21 |
| UIGEN T3 14B Preview | 40K / 29.5 GB | 106 | 20 |
| Qwen3 14B MLX Bf16 | 40K / 29.6 GB | 161 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than HLeiTR/qwen3_14b_full_15k_ckpt_125 .
Rank the Qwen3 14B Full 15K Ckpt 125 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? 49991 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124