Autotrain compatible Endpoints compatible Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Weyaxi/Nous-Hermes-2-SUS-Chat-2x34B
Nous Hermes 2 SUS Chat 2x34B Benchmarks
ARC: 66.81 vs 96.7 (so35)-30.9%
HellaSwag: 85.22 vs 95.3 (gpt4)-10.6%
MMLU: 76.65 vs 88.3 (so35)-13.2%
TruthfulQA: 57.42 vs 59 (gpt4)-2.7%
WinoGrande: 83.74 vs 87.5 (gpt4)-4.3%
GSM8K: 73.09 vs 96.4 (so35)-24.2%
LLME Score: 0.16014
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)
Nous Hermes 2 SUS Chat 2x34B Parameters and Internals
| LLM Name | Nous Hermes 2 SUS Chat 2x34B |
| Repository 🤗 | https://huggingface.co/Weyaxi/Nous-Hermes-2-SUS-Chat-2x34B |
| Model Size | 60.8b |
| Required VRAM | 121.9 GB |
| Updated | 2025-07-29 |
| Maintainer | Weyaxi |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|startoftext|> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Nous Hermes 2 SUS Chat 2x34B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mixtral 34Bx2 MoE 60B | 195K / 121.9 GB | 9902 | 112 |
| Yi 34Bx2 MoE 60B DPO | 195K / 121.8 GB | 9821 | 3 |
| Bagel Hermes 2x34B | 195K / 121.9 GB | 64 | 16 |
| Yi 34Bx2 MoE 200K | 195K / 121.9 GB | 9833 | 2 |
| Yi 34Bx2 MoE 60B | 195K / 121.9 GB | 9886 | 65 |
| ...34Bx2 MoE V0.1 Full Linear DPO | 195K / 121.8 GB | 10 | 2 |
| FusionNet 34Bx2 MoE V0.1 | 195K / 121.2 GB | 7 | 8 |
| ... Cloudyu Mixtral 34Bx2 MoE 60B | 195K / 121.8 GB | 7 | 0 |
| FusionNet 34Bx2 MoE | 32K / 121.2 GB | 991 | 8 |
| ...DPO TomGrc FusionNet 34Bx2 MoE | 32K / 121.8 GB | 6 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than Weyaxi/Nous-Hermes-2-SUS-Chat-2x34B .
Rank the Nous Hermes 2 SUS Chat 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! 🌟
What open-source LLMs or SLMs are you in search of? 50230 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124