What are the hardware requirements for Antares 11B V1?

Antares 11B V1 requires approximately 21.4 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Antares 11B V1 and how large is it?

Antares 11B V1 is developed by decapoda-research, 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 Antares 11B V1 perform on standard benchmarks?

Antares 11B V1 has the following published scores: MMLU 65.96. Compare against reference models on this page or on the LLM Explorer leaderboards.

Antares 11B V1 by decapoda-research — VRAM 21.4GB, 4K context

Name: Antares 11B V1
Author: decapoda-research

Antares 11B V1 is an open-source language model by decapoda-research. Features: 11b LLM, VRAM: 21.4GB, Context: 4K, License: cc-by-nc-4.0, Instruction-Based, Merged, LLM Explorer Score: 0.11, Arc: 64.5, HellaSwag: 84.9, MMLU: 66, GSM8K: 58.3.

Merged Model Base model:finetune:upstage/so... Base model:upstage/solar-10.7b... Conversational Dataset:garage-baind/open-plat... Dataset:ldjnr/capybara Dataset:teknium/openhermes Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/decapoda-research/Antares-11b-v1

Antares 11B V1 Parameters and Internals

Additional Notes

Deprecated in favor of decapoda-research/Antares-11b-v2

Training Details

Data Sources:

teknium/openhermes, garage-bAInd/Open-Platypus, LDJnr/Capybara

LLM Name	Antares 11B V1
Repository 🤗	https://huggingface.co/decapoda-research/Antares-11b-v1
Base Model(s)	upstage/SOLAR-10.7B-Instruct-v1.0 upstage/SOLAR-10.7B-Instruct-v1.0
Merged Model	Yes
Model Size	11b
Required VRAM	21.4 GB
Updated	2026-07-31
Maintainer	decapoda-research
Model Type	llama
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-5 5.0 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 1.7 GB: 5-of-5
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Antares 11B V1 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 Antares 11B V1

Best Alternatives	Context / RAM	Downloads	Likes
A6.1	1024K / 16.1 GB	130	0
...k PL 11B V3.0 Instruct Heretic	32K / 22.3 GB	149	0
Llama 3 11B Instruct RP GLUED	8K / 22.2 GB	4	3
Llama 3 11B Instruct	8K / 22.1 GB	6	3
Llama 3 Synatra 11B V1	8K / 23 GB	7	12
Llama 3 16B Instruct V0.1	8K / 33.5 GB	17	5
SyntheticMoist 11B V2	4K / 21.4 GB	7	3
MedMitsu Instruct 11B	4K / 21.4 GB	9	0
Tengentoppa 11B Instruct	2K / 23.2 GB	9	0
... 11B V2.5 Instruct FP8 Dynamic	32K / 11.5 GB	33	2

Note: green Score (e.g. "73.2") means that the model is better than decapoda-research/Antares-11b-v1.