What are the hardware requirements for Dolphin 2.5 Mixtral 8x7b GPTQ?

Dolphin 2.5 Mixtral 8x7b GPTQ requires approximately 23.8 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 Dolphin 2.5 Mixtral 8x7b GPTQ and how large is it?

Dolphin 2.5 Mixtral 8x7b GPTQ is developed by TheBloke, a model with 46.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Dolphin 2.5 Mixtral 8x7b GPTQ?

Dolphin 2.5 Mixtral 8x7b GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dolphin 2.5 Mixtral 8x7b GPTQ by TheBloke — VRAM 23.8GB, 32K context

Name: Dolphin 2.5 Mixtral 8x7b GPTQ
Author: TheBloke

Dolphin 2.5 Mixtral 8x7b GPTQ is an open-source language model by TheBloke. Features: 46.7b LLM, VRAM: 23.8GB, Context: 32K, License: apache-2.0, MoE, Quantized, Instruction-Based, LLM Explorer Score: 0.11.

4-bit Base model:dphn/dolphin-2.5-mi... Base model:quantized:dphn/dolp... Conversational Dataset:ehartford/dolphin Dataset:ehartford/dolphin-code... Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss... Dataset:jondurbin/airoboros-2.... Dataset:ldjnr/pure-dove Dataset:migtissera/synthia-v1.... Dataset:teknium/openhermes Deploy:azure En Gptq Instruct Mixtral Moe Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ

Dolphin 2.5 Mixtral 8x7b GPTQ Parameters and Internals

LLM Name	Dolphin 2.5 Mixtral 8x7b GPTQ
Repository 🤗	https://huggingface.co/TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ
Model Name	Dolphin 2.5 Mixtral 8X7B
Model Creator	Eric Hartford
Base Model(s)	ehartford/dolphin-2.5-mixtral-8x7b ehartford/dolphin-2.5-mixtral-8x7b
Model Size	46.7b
Required VRAM	23.8 GB
Updated	2026-07-27
Maintainer	TheBloke
Model Type	mixtral
Instruction-Based	Yes
Model Files	23.8 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
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	32002
Torch Data Type	bfloat16

Rank the Dolphin 2.5 Mixtral 8x7b GPTQ 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 Dolphin 2.5 Mixtral 8x7b GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...ixtral 8x7B Instruct V0.1 GPTQ	32K / 23.8 GB	210	141
...xtral Instruct 8x7b Zloss GPTQ	32K / 23.8 GB	7	2
....1 LimaRP ZLoss DARE TIES GPTQ	32K / 23.8 GB	5	6
Dolphin 2.7 Mixtral 8x7b GPTQ	32K / 23.8 GB	32	19
...nstruct V0.1 LimaRP ZLoss GPTQ	32K / 23.8 GB	9	3
...tLM Mixtral 8x7B Instruct GPTQ	32K / 23.8 GB	39	3
... Mixtral 8x7b Instruct V3 GPTQ	32K / 23.8 GB	10	2
...ixtral 8x7B V0.1 Dolly15K GPTQ	32K / 23.8 GB	7	2
Dolphin 2.6 Mixtral 8x7b GPTQ	32K / 23.8 GB	12	6
Mixtral 8x7B Instruct V0.1	32K / 93.6 GB	842893	4720

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ.