What are the hardware requirements for ReMM V2.2 L2 13B EXL2?

ReMM V2.2 L2 13B EXL2 requires approximately 5.4 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 ReMM V2.2 L2 13B EXL2 and how large is it?

ReMM V2.2 L2 13B EXL2 is developed by Anthonyg5005, a model with 13b 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 ReMM V2.2 L2 13B EXL2?

ReMM V2.2 L2 13B EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

ReMM V2.2 L2 13B EXL2 by Anthonyg5005 — VRAM 5.4GB, 4K context

Name: ReMM V2.2 L2 13B EXL2
Author: Anthonyg5005

ReMM V2.2 L2 13B EXL2 is an open-source language model by Anthonyg5005. Features: 13b LLM, VRAM: 5.4GB, Context: 4K, License: cc-by-nc-4.0|llama2, Quantized, LLM Explorer Score: 0.11.

Base model:quantized:undi95/re... Base model:undi95/remm-v2.2-l2... En Exl2 Exllamav2 Llama Llama 2 Mytho Quantized Quantized model Region:us Remm Safetensors

Model Card on HF 🤗: https://huggingface.co/Anthonyg5005/ReMM-v2.2-L2-13B-exl2

ReMM V2.2 L2 13B EXL2 Parameters and Internals

Model Type

text-generation, Quantized Model

Use Cases

Areas:

research

Applications:

Aphrodite Engine, ExUI, KoboldAI, Text Gen Webui

Primary Use Cases:

text generation

Additional Notes

ReMM is a model created by merging various models using the SLERP method.

Supported Languages

en (native)

LLM Name	ReMM V2.2 L2 13B EXL2
Repository 🤗	https://huggingface.co/Anthonyg5005/ReMM-v2.2-L2-13B-exl2
Base Model(s)	Undi95/ReMM-v2.2-L2-13B Undi95/ReMM-v2.2-L2-13B
Model Size	13b
Required VRAM	5.4 GB
Updated	2026-08-25
Maintainer	Anthonyg5005
Model Type	llama
Model Files	5.4 GB
Supported Languages	en
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0\|llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.33.2
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the ReMM V2.2 L2 13B EXL2 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 ReMM V2.2 L2 13B EXL2

Best Alternatives	Context / RAM	Downloads	Likes
Llama13b 32K Illumeet Finetune	32K / 26 GB	5	0
...Maid V3 13B 32K 8.0bpw H8 EXL2	32K / 13.2 GB	8	1
...Maid V3 13B 32K 6.0bpw H6 EXL2	32K / 10 GB	5	1
WhiteRabbitNeo 13B V1	16K / 26 GB	3146	453
CodeLlama 13B Python Fp16	16K / 26 GB	121	25
CodeLlama 13B Fp16	16K / 26 GB	9	67
CodeLlama 13B Instruct Fp16	16K / 26 GB	137	28
Codellama 13B Bnb 4bit	16K / 7.2 GB	129	5
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	113	3
WhiteRabbitNeo 13B V1 4bit Mlx	16K / 7.8 GB	147	2

Note: green Score (e.g. "73.2") means that the model is better than Anthonyg5005/ReMM-v2.2-L2-13B-exl2.