What are the hardware requirements for Claire 7B 0.1 AWQ?

Claire 7B 0.1 AWQ requires approximately 4.8 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Claire 7B 0.1 AWQ and how large is it?

Claire 7B 0.1 AWQ is developed by TheBloke, a model with 7b 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 Claire 7B 0.1 AWQ?

Claire 7B 0.1 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Claire 7B 0.1 AWQ by TheBloke — VRAM 4.8GB, 2K context

Name: Claire 7B 0.1 AWQ
Author: TheBloke

Claire 7B 0.1 AWQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 4.8GB, Context: 2K, License: cc-by-nc-sa-4.0, Quantized, LLM Explorer Score: 0.1.

4-bit Awq Base model:openllm-france/clai... Base model:quantized:openllm-f... Conversational Custom code Endpoints compatible Falcon Fr Pretrained Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/Claire-7B-0.1-AWQ

Claire 7B 0.1 AWQ Parameters and Internals

Model Type

causal decoder

Additional Notes

The model is attuned to French conversational dialogues, potentially generating dialogues with spoken disfluencies.

Supported Languages

fr (native)

Training Details

Data Sources:

assemblée-nationale.fr, theatre-classique.fr, theatregratuit.com, TCOF, CFPP, CFPB, ACSYNT, PFC, Valibel (ORFEO), ESLO, CRFP, OFROM, CID, Rhapsodie, ParisStories, CLAPI, C-ORAL-ROM (ORFEO), LinTO, SUMM-RE, Réunions de travail (ORFEO), FreD, Fleuron (ORFEO), Accueil UBS, OTG

Data Volume:

Cumulative 161.9 million words

Methodology:

Tuning from Falcon-7b using French conversational data

Context Length:

2048

Training Time:

50 GPU hours on 1 A100 80GB GPU

Hardware Used:

1 A100 80GB GPU

Model Architecture:

Causal decoder-only

Input Output

Input Format:

Prompt template: '- Bonjour BotName, {prompt} - Bonjour UserName, '

Accepted Modalities:

text

Output Format:

Text dialogues

LLM Name	Claire 7B 0.1 AWQ
Repository 🤗	https://huggingface.co/TheBloke/Claire-7B-0.1-AWQ
Model Name	Claire 7B 0.1
Model Creator	OpenLLM France
Base Model(s)	OpenLLM-France/Claire-7B-0.1 OpenLLM-France/Claire-7B-0.1
Model Size	7b
Required VRAM	4.8 GB
Updated	2026-08-08
Maintainer	TheBloke
Model Type	falcon
Model Files	4.8 GB
Supported Languages	fr
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	FalconForCausalLM
License	cc-by-nc-sa-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.35.0
Is Biased	0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	65024
Torch Data Type	bfloat16

Rank the Claire 7B 0.1 AWQ 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 Claire 7B 0.1 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Falcon 7B Instruct Bnb 8bit	2K / 7.2 GB	6	1
Falcon 7B Instruct Bnb 4bit	2K / 4 GB	1	1
...n 7B Instruct Bnb 8bit Smashed	0K / 7.2 GB	19	0
F1H10M 0000	2K / 13.9 GB	2529	0
Saqr 7B Merged	2K / 13.9 GB	232	1
Claire 7B FR Instruct 0.1	2K / 13.9 GB	11	6
DociproLLM 7B	2K / 27.8 GB	13	0
... Openassistant Toxicity Reduce	2K / 30.4 GB	8	0
F1H10M 0000	2K / 13.9 GB	14	0
Falcon Chatbot	2K / 5.5 GB	4	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Claire-7B-0.1-AWQ.