Model Card on HF 🤗: https://huggingface.co/LoneStriker/FusionNet_7Bx2_MoE_14B-6.0bpw-h6-exl2
FusionNet 7Bx2 MoE 14B 6.0bpw H6 EXL2 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)
FusionNet 7Bx2 MoE 14B 6.0bpw H6 EXL2 Parameters and Internals
| Additional Notes |
| |||
| Supported Languages |
| |||
| Training Details |
|
| LLM Name | FusionNet 7Bx2 MoE 14B 6.0bpw H6 EXL2 |
| Repository 🤗 | https://huggingface.co/LoneStriker/FusionNet_7Bx2_MoE_14B-6.0bpw-h6-exl2 |
| Model Size | 14b |
| Required VRAM | 9.8 GB |
| Updated | 2025-12-16 |
| Maintainer | LoneStriker |
| Model Type | mixtral |
| Model Files | |
| Supported Languages | en |
| Quantization Type | exl2 |
| Model Architecture | MixtralForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to FusionNet 7Bx2 MoE 14B 6.0bpw H6 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...et 7Bx2 MoE 14B 4.0bpw H6 EXL2 | 32K / 6.7 GB | 0 | 1 |
| LHK DPO V1 GGUF | 32K / 6.2 GB | 99 | 5 |
| LHK DPO V1 | 32K / 7.8 GB | 9 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/FusionNet_7Bx2_MoE_14B-6.0bpw-h6-exl2 .
Rank the FusionNet 7Bx2 MoE 14B 6.0bpw H6 EXL2 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? 51611 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124