What are the hardware requirements for Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B?

Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B requires approximately 121.8 GB of VRAM and supports a context window of 195K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B and how large is it?

Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B is developed by cloudyu, a model with 60.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B perform on standard benchmarks?

Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B has the following published scores: MMLU 77.28. Compare against reference models on this page or on the LLM Explorer leaderboards.

Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B by cloudyu — VRAM 121.8GB, 195K context

Name: Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B
Author: cloudyu

Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B is an open-source language model by cloudyu. Features: 60.8b LLM, VRAM: 121.8GB, Context: 195K, License: mit, MoE, LLM Explorer Score: 0.11, Arc: 71.3, HellaSwag: 85.2, MMLU: 77.3, GSM8K: 74.1.

Dpo Endpoints compatible Mixtral Moe Region:us Rl-tuned Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/cloudyu/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B

Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B Parameters and Internals

Model Type

moe, DPO, RL-TUNED

Additional Notes

Supports the DPO Trainer for training language models from preference data.

Training Details

Data Sources:

jondurbin/truthy-dpo-v0.1

Methodology:

Direct Preference Optimization

LLM Name	Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B
Repository 🤗	https://huggingface.co/cloudyu/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B
Model Size	60.8b
Required VRAM	121.8 GB
Updated	2026-07-31
Maintainer	cloudyu
Model Type	mixtral
Model Files	4.9 GB: 1-of-25 4.8 GB: 2-of-25 4.9 GB: 3-of-25 4.8 GB: 4-of-25 4.9 GB: 5-of-25 4.8 GB: 6-of-25 4.9 GB: 7-of-25 5.0 GB: 8-of-25 5.0 GB: 9-of-25 5.0 GB: 10-of-25 5.0 GB: 11-of-25 5.0 GB: 12-of-25 5.0 GB: 13-of-25 5.0 GB: 14-of-25 5.0 GB: 15-of-25 5.0 GB: 16-of-25 5.0 GB: 17-of-25 5.0 GB: 18-of-25 5.0 GB: 19-of-25 5.0 GB: 20-of-25 5.0 GB: 21-of-25 5.0 GB: 22-of-25 5.0 GB: 23-of-25 5.0 GB: 24-of-25 2.8 GB: 25-of-25
Model Architecture	MixtralForCausalLM
License	mit
Context Length	200000
Model Max Length	200000
Transformers Version	4.37.1
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	64000
Torch Data Type	bfloat16

Rank the Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Truthful DPO Cloudyu Mixtral 34Bx2 MoE 60B

Best Alternatives	Context / RAM	Downloads	Likes
Mixtral 34Bx2 MoE 60B	195K / 121.9 GB	7876	114
Yi 34Bx2 MoE 60B DPO	195K / 121.8 GB	8035	3
Bagel Hermes 2x34B	195K / 121.9 GB	70	16
Yi 34Bx2 MoE 200K	195K / 121.9 GB	7897	2
Yi 34Bx2 MoE 60B	195K / 121.9 GB	7954	64
...34Bx2 MoE V0.1 Full Linear DPO	195K / 121.8 GB	68	2
FusionNet 34Bx2 MoE V0.1	195K / 121.2 GB	52	8
...DPO TomGrc FusionNet 34Bx2 MoE	32K / 121.8 GB	81	4
FusionNet 34Bx2 MoE	32K / 121.2 GB	65	9
Nous Hermes 2 MoE 2x34B	4K / 121.9 GB	96	0

Note: green Score (e.g. "73.2") means that the model is better than cloudyu/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B.