Bagel Hermes 2x34b GPTQ is an open-source language model by TheBloke. Features: 60.8b LLM, VRAM: 31.8GB, Context: 195K, License: other, MoE, Quantized, LLM Explorer Score: 0.11.
4-bit Base model:quantized:weyaxi/ba... Base model:weyaxi/bagel-hermes... Conversational Gptq Mixtral Moe Quantized Region:us Safetensors Yi
Model Card on HF π€: https://huggingface.co/TheBloke/Bagel-Hermes-2x34b-GPTQ
Bagel Hermes 2x34b GPTQ 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)
π Advertise your project π
Bagel Hermes 2x34b GPTQ Parameters and Internals
| LLM Name | Bagel Hermes 2x34b GPTQ |
| Repository π€ | https://huggingface.co/TheBloke/Bagel-Hermes-2x34b-GPTQ |
| Model Name | Bagel Hermes 2X34B |
| Model Creator | YaΔΔ±z ÇalΔ±k |
| Base Model(s) | |
| Model Size | 60.8b |
| Required VRAM | 31.8 GB |
| Updated | 2026-01-22 |
| Maintainer | TheBloke |
| Model Type | mixtral |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MixtralForCausalLM |
| License | other |
| Context Length | 200000 |
| Model Max Length | 200000 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Bagel Hermes 2x34b GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mixtral 34Bx2 MoE 60B GPTQ | 195K / 31.8 GB | 3 | 7 |
| FusionNet 34Bx2 MoE GPTQ | 32K / 31.8 GB | 7 | 2 |
| ...sionNet 34Bx2 MoE V0.1 DPO F16 | 195K / 121.8 GB | 8509 | 15 |
| 60B MoE Coder V3 | 195K / 121.8 GB | 80 | 3 |
| Mixtral 34Bx2 MoE 60B | 195K / 121.9 GB | 8683 | 111 |
| Yi 34Bx2 MoE 60B DPO | 195K / 121.8 GB | 8225 | 3 |
| Bagel Hermes 2x34B | 195K / 121.9 GB | 105 | 16 |
| Yi 34Bx2 MoE 200K | 195K / 121.9 GB | 8234 | 2 |
| Yi 34Bx2 MoE 60B | 195K / 121.9 GB | 8155 | 64 |
| ...34Bx2 MoE V0.1 Full Linear DPO | 195K / 121.8 GB | 106 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Bagel-Hermes-2x34b-GPTQ .
Rank the Bagel Hermes 2x34b GPTQ Capabilities
π 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! π
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum β our secure, self-hosted AI agent for server management.
Release v20260328a