What are the hardware requirements for Candle Dolphin 2.2.1 Mistral 7B?

Candle Dolphin 2.2.1 Mistral 7B requires approximately 14.4 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 Candle Dolphin 2.2.1 Mistral 7B and how large is it?

Candle Dolphin 2.2.1 Mistral 7B is developed by DanielClough, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Candle Dolphin 2.2.1 Mistral 7B perform on standard benchmarks?

Candle Dolphin 2.2.1 Mistral 7B has the following published scores: MMLU 62.9, LMSYS ELO 1152. Compare against reference models on this page or on the LLM Explorer leaderboards.

Candle Dolphin 2.2.1 Mistral 7B by DanielClough — VRAM 14.4GB, 32K context

Name: Candle Dolphin 2.2.1 Mistral 7B
Author: DanielClough

Candle Dolphin 2.2.1 Mistral 7B is an open-source language model by DanielClough. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.23, ELO: 1152, Arc: 88.2, HellaSwag: 79.7, MMLU: 62.9, GSM8K: 61.9.

Dataset:ehartford/dolphin-2.2.... En Endpoints compatible Gguf Mistral Q4 Quantized Region:us Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/DanielClough/Candle_dolphin-2.2.1-mistral-7b

Candle Dolphin 2.2.1 Mistral 7B Benchmarks

LMSys ELO 1152 vs 1272 (so35) -9.4%

^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)

Candle Dolphin 2.2.1 Mistral 7B Parameters and Internals

Model Type

text-generation

Additional Notes

This repo includes `.gguf` built for HuggingFace/Candle and will not work with `llama.cpp`.

Supported Languages

en (native)

LLM Name	Candle Dolphin 2.2.1 Mistral 7B
Repository 🤗	https://huggingface.co/DanielClough/Candle_dolphin-2.2.1-mistral-7b
Base Model(s)	wasertech/assistant-dolphin-2.2.1-mistral-7b-e1-qlora wasertech/assistant-dolphin-2.2.1-mistral-7b-e1-qlora
Model Size	7b
Required VRAM	14.4 GB
Updated	2026-08-22
Maintainer	DanielClough
Model Type	mistral
Model Files	14.5 GB 2.4 GB 3.1 GB 4.1 GB 4.5 GB 4.1 GB 5.0 GB 5.4 GB 5.0 GB 5.9 GB 7.7 GB 8.2 GB 8.3 GB 9.9 GB: 1-of-2 4.5 GB: 2-of-2
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	q4\|gguf
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.34.1
Vocabulary Size	32002
Torch Data Type	bfloat16

Rank the Candle Dolphin 2.2.1 Mistral 7B 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 Candle Dolphin 2.2.1 Mistral 7B

Best Alternatives	Context / RAM	Downloads	Likes
MegaBeam Mistral 7B 300K Gguf	282K / 5 GB	35	3
MegaBeam Mistral 7B 300K Gguf	282K / 5 GB	34	3
Backrooms Mistral 7B 10e	32K / 14.5 GB	128	0
Mistral 7B Instruct V0.2.gguf	32K / 14.5 GB	17	3
Mistral 7B Instruct V0.2 GGUF	32K / 4.4 GB	26	2
...andle Mistral 7B Instruct V0.2	32K / 14.4 GB	167	0
Boptruth Agatha 7B	32K / 14.4 GB	129	0
Mahou 1.2a Mistral 7B	32K / 14.4 GB	33	7
Tamil Mistral 7B Instruct V0.1	32K / 14.8 GB	350	14
... Noromaid NSFW Mistral 7B GGUF	32K / 4.1 GB	35298	124

Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_dolphin-2.2.1-mistral-7b.