Merged Model Autotrain compatible Base model:flemmingmiguel/mbx-... Base model:paulml/omnibeaglemb... Endpoints compatible Flemmingmiguel/mbx-7b-v3 Mistral Paulml/omnibeaglembx-v3-7b Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/paulml/OmniBeagleSquaredMBX-v3-7B-v2
OmniBeagleSquaredMBX V3 7B V2 Benchmarks
ARC: 74.06 vs 96.7 (so35)-23.4%
HellaSwag: 88.93 vs 95.3 (gpt4)-6.7%
MMLU: 64.53 vs 88.3 (so35)-26.9%
TruthfulQA: 72.93 vs 59 (gpt4)23.6%
WinoGrande: 85.56 vs 87.5 (gpt4)-2.2%
GSM8K: 69.9 vs 96.4 (so35)-27.5%
LLME Score: 0.14757
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)
OmniBeagleSquaredMBX V3 7B V2 Parameters and Internals
| LLM Name | OmniBeagleSquaredMBX V3 7B V2 |
| Repository 🤗 | https://huggingface.co/paulml/OmniBeagleSquaredMBX-v3-7B-v2 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2025-07-31 |
| Maintainer | paulml |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to OmniBeagleSquaredMBX V3 7B V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Nemo Instruct 2407 Abliterated | 1000K / 24.5 GB | 396 | 18 |
| MegaBeam Mistral 7B 512K | 512K / 14.4 GB | 9551 | 50 |
| SpydazWeb AI HumanAI RP | 512K / 14.4 GB | 10 | 1 |
| SpydazWeb AI HumanAI 002 | 512K / 14.4 GB | 18 | 1 |
| ...daz Web AI ChatML 512K Project | 512K / 14.5 GB | 12 | 0 |
| MegaBeam Mistral 7B 300K | 282K / 14.4 GB | 3779 | 16 |
| MegaBeam Mistral 7B 300K | 282K / 14.4 GB | 8339 | 16 |
| Hebrew Mistral 7B 200K | 256K / 30 GB | 1337 | 15 |
| Astral 256K 7B V2 | 250K / 14.4 GB | 5 | 0 |
| Astral 256K 7B | 250K / 14.4 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than paulml/OmniBeagleSquaredMBX-v3-7B-v2 .
Rank the OmniBeagleSquaredMBX V3 7B V2 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? 50263 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124