What are the hardware requirements for Laser Dolphin Mixtral 2x7b DPO?

Laser Dolphin Mixtral 2x7b DPO requires approximately 25.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Laser Dolphin Mixtral 2x7b DPO and how large is it?

Laser Dolphin Mixtral 2x7b DPO is developed by macadeliccc, a model with 12.9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Laser Dolphin Mixtral 2x7b DPO perform on standard benchmarks?

Laser Dolphin Mixtral 2x7b DPO has the following published scores: MMLU 63.17. Compare against reference models on this page or on the LLM Explorer leaderboards.

Laser Dolphin Mixtral 2x7b DPO by macadeliccc — VRAM 25.8GB, 32K context

Name: Laser Dolphin Mixtral 2x7b DPO
Author: macadeliccc

Laser Dolphin Mixtral 2x7b DPO is an open-source language model by macadeliccc. Features: 12.9b LLM, VRAM: 25.8GB, Context: 32K, License: apache-2.0, MoE, LLM Explorer Score: 0.12, Arc: 66, HellaSwag: 85.8, MMLU: 63.2, GSM8K: 48.3.

Arxiv:2312.13558 Endpoints compatible Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/macadeliccc/laser-dolphin-mixtral-2x7b-dpo

Laser Dolphin Mixtral 2x7b DPO Parameters and Internals

Model Type

MoE implementation, text-generation

Use Cases

Areas:

Research, Commercial Applications

Additional Notes

Laser-Dolphin Mixtral is a medium-sized MoE model based on Dolphin model with enhancements and quantizations for better performance.

Input Output

Accepted Modalities:

text

Output Format:

Text generation outputs

Release Notes

Date:

2024-01-31

Notes:

Evaluation Score (v2): 72.76 with increased performance.

LLM Name	Laser Dolphin Mixtral 2x7b DPO
Repository 🤗	https://huggingface.co/macadeliccc/laser-dolphin-mixtral-2x7b-dpo
Model Size	12.9b
Required VRAM	25.8 GB
Updated	2026-07-27
Maintainer	macadeliccc
Model Type	mixtral
Model Files	9.9 GB: 1-of-3 10.0 GB: 2-of-3 5.9 GB: 3-of-3
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Laser Dolphin Mixtral 2x7b DPO 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

Quantized Models of the Laser Dolphin Mixtral 2x7b DPO

Model	Likes	Downloads	VRAM
... Dolphin Mixtral 2x7b DPO GGUF	50	1630	4 GB
... Dolphin Mixtral 2x7b DPO GPTQ	11	6	7 GB
...r Dolphin Mixtral 2x7b DPO AWQ	9	8	7 GB

Best Alternatives to Laser Dolphin Mixtral 2x7b DPO

Best Alternatives	Context / RAM	Downloads	Likes
MixTAO 7Bx2 MoE V8.1	32K / 25.8 GB	15381	56
Inf Silent Kunoichi V0.1 2x7B	32K / 25.6 GB	8	0
Inf Silent Kunoichi V0.2 2x7B	32K / 25.6 GB	9	1
LogoS 7Bx2 MoE 13B V0.2	32K / 25.9 GB	7978	10
MixTAO 7Bx2 MoE V8.1	32K / 25.8 GB	8760	52
MultiMash8 13B Slerp	32K / 25.7 GB	5	0
MultiMash11 13B Slerp	32K / 25.7 GB	9	0
MultiMash9 13B Slerp	32K / 25.7 GB	5	0
MultiMash10 13B Slerp	32K / 25.7 GB	8	0
Multimash3 12B Slerp	32K / 25.7 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than macadeliccc/laser-dolphin-mixtral-2x7b-dpo.