What are the hardware requirements for Quantized Kheopss AWQ 4bits V1?

Quantized Kheopss AWQ 4bits V1 requires approximately 4.2 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 Quantized Kheopss AWQ 4bits V1 and how large is it?

Quantized Kheopss AWQ 4bits V1 is developed by kheopss, a model with 1.2b 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 Quantized Kheopss AWQ 4bits V1?

Quantized Kheopss AWQ 4bits V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Quantized Kheopss AWQ 4bits V1 by kheopss — VRAM 4.2GB, 32K context

Name: Quantized Kheopss AWQ 4bits V1
Author: kheopss

Quantized Kheopss AWQ 4bits V1 is an open-source language model by kheopss. Features: 1.2b LLM, VRAM: 4.2GB, Context: 32K, Quantized, LLM Explorer Score: 0.13.

16bit 4-bit Autotrain compatible Awq Conversational Endpoints compatible Mistral Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/kheopss/quantized_kheopss_AWQ_4bits_V1

Quantized Kheopss AWQ 4bits V1 Parameters and Internals

LLM Name	Quantized Kheopss AWQ 4bits V1
Repository 🤗	https://huggingface.co/kheopss/quantized_kheopss_AWQ_4bits_V1
Model Size	1.2b
Required VRAM	4.2 GB
Updated	2024-08-08
Maintainer	kheopss
Model Type	mistral
Model Files	4.2 GB
AWQ Quantization	Yes
Quantization Type	awq\|16bit
Model Architecture	MistralForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.43.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32002
Torch Data Type	float16

Rank the Quantized Kheopss AWQ 4bits 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 Quantized Kheopss AWQ 4bits V1

Best Alternatives	Context / RAM	Downloads	Likes
MistralLite AWQ	32K / 4.2 GB	42	3
SFR Embedding Mistral AWQ	32K / 4.2 GB	16	0
Yugo55A GPT AWQ	32K / 4.2 GB	6	0
Openchat 3.5 16K AWQ	32K / 4.2 GB	3	1
Openchat 3.5 0106 AWQ	8K / 4.2 GB	3	1
Hare1.0 Beta	32K / 2.4 GB	50	1
Mistralmawq	32K / 4.2 GB	14	0
... Finetune 16bit Ver9 Main GPTQ	32K / 4.2 GB	6	0
Turdus GPTQ	32K / 4.2 GB	8	5

Note: green Score (e.g. "73.2") means that the model is better than kheopss/quantized_kheopss_AWQ_4bits_V1.