What are the hardware requirements for Beef 12B?

Beef 12B requires approximately 3.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Beef 12B and how large is it?

Beef 12B is developed by hardlyworking, a model with 12b 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 Beef 12B?

Beef 12B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Beef 12B by hardlyworking — VRAM 3.6GB

Name: Beef 12B
Author: hardlyworking

Beef 12B is an open-source language model by hardlyworking. Features: 12b LLM, VRAM: 3.6GB, Merged, LLM Explorer Score: 0.17.

Merged Model Adapter Axolotl Base model:adapter:hardlyworki... Base model:hardlyworking/noodl... Dataset:anthracite-core/c2 log... Dataset:epiculous/synthrp-gens... Dataset:hardlyworking/openerot... Dataset:minervaai/aesir-previe... Dataset:nitral-ai/creative wri... Dataset:pjmixers/lodrick-the-l... Dataset:resplendentai/bluemoon Finetuned Generated from trainer Lora Mistral Peft Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/hardlyworking/Beef-12B

Beef 12B Parameters and Internals

LLM Name	Beef 12B
Repository 🤗	https://huggingface.co/hardlyworking/Beef-12B
Base Model(s)	Noodles Merge 12B hardlyworking/Noodles-Merge-12B
Merged Model	Yes
Model Size	12b
Required VRAM	3.6 GB
Updated	2025-10-20
Maintainer	hardlyworking
Model Files	3.6 GB 0.0 GB
Model Architecture	Adapter
Is Biased	none
Tokenizer Class	PreTrainedTokenizer
Padding Token	<pad>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	o_proj\|down_proj\|gate_proj\|up_proj\|k_proj\|q_proj\|v_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	128

Rank the Beef 12B 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 Beef 12B

Best Alternatives	Context / RAM	Downloads	Likes
Teleste Learner 12B	0K / 0.3 GB	775	1
...ni 3.5 Flash Reasoning Distill	0K / 0.3 GB	13	1
Noodles 12B	0K / 3.6 GB	5	0
G3 12B Pt Story Qlora	0K / 0.5 GB	23	0
CEV Other 12B Lora	0K / 0.1 GB	5	0
Meme 12B Lora E2	0K / 0.2 GB	8	0
Meme 12B Lora E2	0K / 0.2 GB	5	0
Control 12B R3 Lora	0K / 2.9 GB	6	0
Control 12B R3 Lora	0K / 2.9 GB	5	0
...Noctis R64 Test Train Lora 12B	0K / 0.9 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than hardlyworking/Beef-12B.