Merged Model Arxiv:2403.19522 Autotrain compatible Base model:lunzima/nqlsg-qwen2... Base model:prithivmlmods/equul... Base model:sakalti/saka-14b Base model:suayptalha/lamarckv... Base model:suayptalha/lix-14b-... Base model:wanlige/li-14b-v0.4 Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1
NQLSG Qwen2.5 14B MegaFusion V9.1 Benchmarks
MMLU Pro: 47.23
GPQA: 12.42
MUSR: 14.76
BBH: 50.74
IFEval: 80.03 vs 88 (so35)-9.1%
MATH Lvl 5: 54.68
LLME Score: 0.34775
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)
NQLSG Qwen2.5 14B MegaFusion V9.1 Parameters and Internals
| LLM Name | NQLSG Qwen2.5 14B MegaFusion V9.1 |
| Repository 🤗 | https://huggingface.co/Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 14b |
| Required VRAM | 29.7 GB |
| Updated | 2025-07-29 |
| Maintainer | Lunzima |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151665 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to NQLSG Qwen2.5 14B MegaFusion V9.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 14B Instruct 1M | 986K / 29.6 GB | 21467 | 315 |
| T3Q Qwen2.5 14B V1.0 E3 | 986K / 29.7 GB | 852 | 28 |
| ZYH LLM Qwen2.5 14B V4 | 986K / 29.7 GB | 727 | 8 |
| ZYH LLM Qwen2.5 14B V3 | 986K / 29.7 GB | 388 | 8 |
| Qwen2.5 14B 1M YOYO V3 | 986K / 29.7 GB | 254 | 4 |
| Impish QWEN 14B 1M | 986K / 29.7 GB | 353 | 16 |
| Qwen2.5 14B YOYO Latest V2 | 986K / 29.7 GB | 129 | 0 |
| Qwen2.5 14B YOYO V4 | 986K / 29.7 GB | 14 | 5 |
| Etr1o V1.2 | 986K / 29.7 GB | 5 | 0 |
| ...14B Instruct 1M GRPO Reasoning | 986K / 29.7 GB | 9 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1 .
Rank the NQLSG Qwen2.5 14B MegaFusion V9.1 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? 50200 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124