What are the hardware requirements for Dolphin3.0 R1 Mistral 24B 4bit?

Dolphin3.0 R1 Mistral 24B 4bit requires approximately 13.3 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 Dolphin3.0 R1 Mistral 24B 4bit and how large is it?

Dolphin3.0 R1 Mistral 24B 4bit is developed by mlx-community, a model with 24b 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 Dolphin3.0 R1 Mistral 24B 4bit?

Dolphin3.0 R1 Mistral 24B 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dolphin3.0 R1 Mistral 24B 4bit by mlx-community — VRAM 13.3GB, 32K context

Name: Dolphin3.0 R1 Mistral 24B 4bit
Author: mlx-community

Dolphin3.0 R1 Mistral 24B 4bit is an open-source language model by mlx-community. Features: 24b LLM, VRAM: 13.3GB, Context: 32K, Quantized, LLM Explorer Score: 0.17.

4-bit 4bit Base model:dphn/dolphin3.0-r1-... Base model:quantized:dphn/dolp... Conversational Dataset:ai-mo/numinamath-cot Dataset:ai-mo/numinamath-tir Dataset:allenai/tulu-3-sft-mix... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:huggingfacetb/smoltalk Dataset:m-a-p/code-feedback Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-agentin... Dataset:microsoft/orca-math-wo... Dataset:nousresearch/hermes-fu... Dataset:opencoder-llm/opc-sft-... Dataset:opencoder-llm/opc-sft-... En Endpoints compatible Mistral Mlx Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Dolphin3.0-R1-Mistral-24B-4bit

Dolphin3.0 R1 Mistral 24B 4bit Parameters and Internals

LLM Name	Dolphin3.0 R1 Mistral 24B 4bit
Repository 🤗	https://huggingface.co/mlx-community/Dolphin3.0-R1-Mistral-24B-4bit
Base Model(s)	cognitivecomputations/Dolphin3.0-R1-Mistral-24B cognitivecomputations/Dolphin3.0-R1-Mistral-24B
Model Size	24b
Required VRAM	13.3 GB
Updated	2026-07-21
Maintainer	mlx-community
Model Type	mistral
Model Files	5.3 GB: 1-of-3 5.3 GB: 2-of-3 2.7 GB: 3-of-3
Supported Languages	en
Quantization Type	4bit
Model Architecture	MistralForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.48.1
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	131074
Torch Data Type	bfloat16

Rank the Dolphin3.0 R1 Mistral 24B 4bit 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 Dolphin3.0 R1 Mistral 24B 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Morbid Miasma 24B Mlx 8Bit	128K / 25 GB	40	2
Devstral Small 2507 Bnb 4bit	128K / 14.2 GB	398	1
...al Small 2507 Unsloth Bnb 4bit	128K / 15 GB	128	5
...al Small 2506 Unsloth Bnb 4bit	40K / 15 GB	109	4
Magistral Small 2506 Bnb 4bit	40K / 14.2 GB	38	1
...l Small 24B Instruct 2501 4bit	32K / 13.3 GB	1344	14
Not So Small Alpaca 24B	32K / 47.3 GB	14	0
Napoleon 24B V0.0	32K / 47.3 GB	18	0
...all 24B Instruct 2501 Bnb 4bit	32K / 14.2 GB	4725	3
...Instruct 2501 Unsloth Bnb 4bit	32K / 15 GB	2955	19

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Dolphin3.0-R1-Mistral-24B-4bit.