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

Bagel Hermes 2x34B by Weyaxi

 »  All LLMs  »  Weyaxi  »  Bagel Hermes 2x34B   URL Share it on

  136   

Bagel Hermes 2x34B is an open-source language model by Weyaxi. Features: 60.8b LLM, VRAM: 121.9GB, Context: 195K, License: apache-2.0, MoE, LLM Explorer Score: 0.19, Arc: 69.8, HellaSwag: 85.3, MMLU: 77.2, GSM8K: 68.7.

  Conversational   Endpoints compatible   Mixtral   Model-index   Moe   Region:us   Safetensors   Sharded   Tensorflow   Yi
Model Card on HF 🤗: https://huggingface.co/Weyaxi/Bagel-Hermes-2x34B 

Bagel Hermes 2x34B Benchmarks

ARC: 69.8 vs 96.7 (so35)-27.8%
HellaSwag: 85.26 vs 95.3 (gpt4)-10.5%
MMLU: 77.24 vs 88.3 (so35)-12.5%
GSM8K: 68.69 vs 96.4 (so35)-28.7%
LLME Score: 0.19184
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bagel Hermes 2x34B (Weyaxi/Bagel-Hermes-2x34B)
🌟 Advertise your project 🚀

Bagel Hermes 2x34B Parameters and Internals

Model Type 
text-generation
Additional Notes 
Quantized versions available from TheBloke: GPTQ, GGUF, AWQ.
Training Details 
Methodology:
Expert models with gate_mode.
Model Architecture:
Mixture of Experts (MoE)
Input Output 
Performance Tips:
Utilize ChatML and other provided prompt templates for better results.
LLM NameBagel Hermes 2x34B
Repository 🤗https://huggingface.co/Weyaxi/Bagel-Hermes-2x34B 
Model Size60.8b
Required VRAM121.9 GB
Updated2026-05-15
MaintainerWeyaxi
Model Typemixtral
Model Files  9.8 GB: 1-of-13   10.0 GB: 2-of-13   10.0 GB: 3-of-13   10.0 GB: 4-of-13   10.0 GB: 5-of-13   10.0 GB: 6-of-13   10.0 GB: 7-of-13   10.0 GB: 8-of-13   10.0 GB: 9-of-13   10.0 GB: 10-of-13   10.0 GB: 11-of-13   10.0 GB: 12-of-13   2.1 GB: 13-of-13
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length200000
Model Max Length200000
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Bagel Hermes 2x34B

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 34Bx2 MoE 60B195K / 121.9 GB8261114
Yi 34Bx2 MoE 60B DPO195K / 121.8 GB82563
Yi 34Bx2 MoE 200K195K / 121.9 GB80962
Yi 34Bx2 MoE 60B195K / 121.9 GB836564
...34Bx2 MoE V0.1 Full Linear DPO195K / 121.8 GB1062
FusionNet 34Bx2 MoE V0.1195K / 121.2 GB898
... Cloudyu Mixtral 34Bx2 MoE 60B195K / 121.8 GB1000
FusionNet 34Bx2 MoE32K / 121.2 GB2499
...DPO TomGrc FusionNet 34Bx2 MoE32K / 121.8 GB814
Nous Hermes 2 MoE 2x34B4K / 121.9 GB1890
Note: green Score (e.g. "73.2") means that the model is better than Weyaxi/Bagel-Hermes-2x34B.

Rank the Bagel Hermes 2x34B 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? 53972 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer