What are the hardware requirements for CarbonBeagle 11B?

CarbonBeagle 11B requires approximately 21.4 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 CarbonBeagle 11B and how large is it?

CarbonBeagle 11B is developed by vicgalle, a model with 11b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CarbonBeagle 11B perform on standard benchmarks?

CarbonBeagle 11B has the following published scores: MMLU 66.62. Compare against reference models on this page or on the LLM Explorer leaderboards.

CarbonBeagle 11B by vicgalle — VRAM 21.4GB, 32K context

Name: CarbonBeagle 11B
Author: vicgalle

CarbonBeagle 11B is an open-source language model by vicgalle. Features: 11b LLM, VRAM: 21.4GB, Context: 32K, License: cc-by-nc-sa-4.0, Merged, LLM Explorer Score: 0.21, Arc: 71.8, HellaSwag: 88.9, MMLU: 66.6, GSM8K: 66.9.

Merged Model Arxiv:2203.05482 Base model:jeonsworld/carbonvi... Base model:vicgalle/neuralbeag... Conversational Deploy:azure Endpoints compatible Mistral Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/vicgalle/CarbonBeagle-11B

CarbonBeagle 11B Parameters and Internals

Model Type

text generation

Additional Notes

An experiment in merging models of different architectures and sizes. The merging utilized the linear method, combining vicgalle/NeuralBeagle-11B with weight 0.5 and jeonsworld/CarbonVillain-en-10.7B-v4 with weight 1.0.

LLM Name	CarbonBeagle 11B
Repository 🤗	https://huggingface.co/vicgalle/CarbonBeagle-11B
Base Model(s)	NeuralBeagle 11B jeonsworld/CarbonVillain-en-10.7B-v4 vicgalle/NeuralBeagle-11B jeonsworld/CarbonVillain-en-10.7B-v4
Merged Model	Yes
Model Size	11b
Required VRAM	21.4 GB
Updated	2026-07-24
Maintainer	vicgalle
Model Type	mistral
Model Files	9.9 GB: 1-of-3 9.8 GB: 2-of-3 1.7 GB: 3-of-3
Model Architecture	MistralForCausalLM
License	cc-by-nc-sa-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the CarbonBeagle 11B 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 CarbonBeagle 11B

Best Alternatives	Context / RAM	Downloads	Likes
Starling LM 11B Alpha	32K / 21.4 GB	100	15
...elik V2.3 Instruct MedIT Merge	32K / 22.3 GB	1592	2
Normistral 11B Translate	32K / 22.8 GB	193	1
ConfigurableBeagle 11B	32K / 21.4 GB	8206	3
...elik V2.3 Instruct Llama Prune	32K / 15.4 GB	1387	0
CarbonBeagle 11B Truthy	32K / 21.4 GB	7713	10
MistralLite 11B	32K / 21.4 GB	1337	2
Mistral 11B Instruct V0.1	32K / 42.9 GB	169	2
Mistral Evolved 11B V0.1	32K / 22.3 GB	58	33
Mistral 11B Miniplatypus	32K / 21.5 GB	9	0

Note: green Score (e.g. "73.2") means that the model is better than vicgalle/CarbonBeagle-11B.