What are the hardware requirements for CausalLM 14B EXL2?

CausalLM 14B EXL2 requires approximately 8.5 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CausalLM 14B EXL2 and how large is it?

CausalLM 14B EXL2 is developed by cgus, a model with 14b 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 CausalLM 14B EXL2?

CausalLM 14B EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

CausalLM 14B EXL2 by cgus — VRAM 8.5GB, 8K context

Name: CausalLM 14B EXL2
Author: cgus

CausalLM 14B EXL2 is an open-source language model by cgus. Features: 14b LLM, VRAM: 8.5GB, Context: 8K, License: wtfpl, Quantized, Instruction-Based, LLM Explorer Score: 0.09.

Base model:causallm/14b Base model:finetune:causallm/1... Dataset:baai/coig Dataset:fnlp/moss-003-sft-data Dataset:garage-baind/open-plat... Dataset:jondurbin/airoboros-3.... Dataset:josephuscheung/guanaco... Dataset:ldjnr/puffin Dataset:liuhaotian/llava-instr... Dataset:liwu/mnbvc Dataset:meta-math/metamathqa Dataset:milashkaarshif/moegirl... Dataset:open-orca/openorca Dataset:openbmb/llava zh Dataset:ryokoai/fandom23k Dataset:ryokoai/sharegpt52k Dataset:stingning/ultrachat Dataset:teknium/openhermes Dataset:tigerresearch/tigerbot... Dataset:wiki lingua Dataset:wikipedia Dataset:wizardlm/wizardlm evol... En Exl2 Instruct Llama Llama2 Quantized Region:us Zh

Model Card on HF 🤗: https://huggingface.co/cgus/CausalLM-14B-exl2

CausalLM 14B EXL2 Parameters and Internals

LLM Name	CausalLM 14B EXL2
Repository 🤗	https://huggingface.co/cgus/CausalLM-14B-exl2
Model Name	CausalLM 14B
Model Creator	CausalLM
Base Model(s)	14B CausalLM/14B
Model Size	14b
Required VRAM	8.5 GB
Updated	2026-07-31
Maintainer	cgus
Model Type	llama
Instruction-Based	Yes
Model Files	8.5 GB
Supported Languages	en zh
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
License	wtfpl
Context Length	8192
Model Max Length	8192
Transformers Version	4.34.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	152064
Torch Data Type	float16
Errors	replace

Rank the CausalLM 14B 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 CausalLM 14B EXL2

Best Alternatives	Context / RAM	Downloads	Likes
...struct 2512 Llamafied TextOnly	256K / 27 GB	9	3
...hocolatine 2 14B Instruct V2.0	16K / 29.4 GB	11	6
...colatine 2 14B Instruct V2.0.1	16K / 29.4 GB	30	1
14B	8K / 28.4 GB	222	313
CausalLM 14B GPTQ	8K / 9.7 GB	59	20
CausalLM 14B AWQ	8K / 9.7 GB	48	10

Note: green Score (e.g. "73.2") means that the model is better than cgus/CausalLM-14B-exl2.