LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

FMixIA FrankenMerge 9.5B PT 9 by Ro-xe

 »  All LLMs  »  Ro-xe  »  FMixIA FrankenMerge 9.5B PT 9   URL Share it on

  3   
  Merged Model   7b   Passthrough   Qwen2   Region:us   Safetensors   Sharded   Tensorflow Zeroxclem/qwen2.5-7b-homeranvi... Zeroxclem/qwen2.5-7b-homercrea...
Model Card on HF 🤗: https://huggingface.co/Ro-xe/FMixIA-FrankenMerge-9.5B-PT-9 

FMixIA FrankenMerge 9.5B PT 9 Benchmarks

MMLU Pro: 29.52
GPQA: 7.72
MUSR: 9.46
BBH: 30.71
IFEval: 19.4 vs 88 (so35)-78%
MATH Lvl 5: 0.3
LLME Score: 0.26749
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
FMixIA FrankenMerge 9.5B PT 9 (Ro-xe/FMixIA-FrankenMerge-9.5B-PT-9)

FMixIA FrankenMerge 9.5B PT 9 Parameters and Internals

LLM NameFMixIA FrankenMerge 9.5B PT 9
Repository 🤗https://huggingface.co/Ro-xe/FMixIA-FrankenMerge-9.5B-PT-9 
Merged ModelYes
Model Size7b
Required VRAM41 GB
Updated2025-04-23
MaintainerRo-xe
Model Typeqwen2
Model Files  1.0 GB: 1-of-15   1.1 GB: 1-of-30   1.0 GB: 2-of-15   1.1 GB: 2-of-30   1.0 GB: 3-of-15   0.9 GB: 3-of-30   1.0 GB: 4-of-15   0.9 GB: 4-of-30   0.9 GB: 5-of-15   0.9 GB: 5-of-30   1.0 GB: 6-of-15   0.9 GB: 6-of-30   1.0 GB: 7-of-15   0.9 GB: 7-of-30   1.0 GB: 8-of-15   0.9 GB: 8-of-30   0.9 GB: 9-of-15   0.9 GB: 9-of-30   1.0 GB: 10-of-15   0.9 GB: 10-of-30   1.0 GB: 11-of-15   0.9 GB: 11-of-30   1.0 GB: 12-of-15   0.9 GB: 12-of-30   0.9 GB: 13-of-15   0.9 GB: 13-of-30   1.0 GB: 14-of-15   0.9 GB: 14-of-30   0.8 GB: 15-of-15   0.9 GB: 15-of-30   0.9 GB: 16-of-30   0.9 GB: 17-of-30   0.9 GB: 18-of-30   0.9 GB: 19-of-30   0.9 GB: 20-of-30   0.9 GB: 21-of-30   0.9 GB: 22-of-30   0.9 GB: 23-of-30   0.9 GB: 24-of-30   0.9 GB: 25-of-30   0.9 GB: 26-of-30   0.9 GB: 27-of-30   0.9 GB: 28-of-30   0.9 GB: 29-of-30
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.47.0
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to FMixIA FrankenMerge 9.5B PT 9

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB2571997315
Hush Qwen2.5 7B Preview986K / 15.2 GB2510
Hush Qwen2.5 7B V1.2986K / 15.2 GB91
Hush Qwen2.5 7B V1.1986K / 15.2 GB91
Hush Qwen2.5 7B V1.4986K / 15.2 GB101
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB292
Hush Qwen2.5 7B V1.3986K / 15.2 GB92
Qwen2.5 7B RRP 1M986K / 15.2 GB646
Qwen2.5 7B Preview986K / 15.2 GB60
Qwen2.5 7B MixStock V0.1986K / 15.2 GB163
Note: green Score (e.g. "73.2") means that the model is better than Ro-xe/FMixIA-FrankenMerge-9.5B-PT-9.

Rank the FMixIA FrankenMerge 9.5B PT 9 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 46599 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer