What are the hardware requirements for AdaptLLM Finance Chat AWQ?

AdaptLLM Finance Chat AWQ requires approximately 3.9 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 AdaptLLM Finance Chat AWQ and how large is it?

AdaptLLM Finance Chat AWQ is developed by msamon, a model with 6.7b 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 AdaptLLM Finance Chat AWQ?

AdaptLLM Finance Chat AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

AdaptLLM Finance Chat AWQ by msamon — VRAM 3.9GB, 4K context

Name: AdaptLLM Finance Chat AWQ
Author: msamon

AdaptLLM Finance Chat AWQ is an open-source language model by msamon. Features: 6.7b LLM, VRAM: 3.9GB, Context: 4K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.1.

Arxiv:2309.09530 4-bit Awq Dataset:gair/lima Dataset:open-orca/openorca Dataset:wizardlm/wizardlm evol... En Endpoints compatible Finance Instruct Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/msamon/AdaptLLM-finance-chat-AWQ

AdaptLLM Finance Chat AWQ Parameters and Internals

Model Type

text-generation, domain-specific

Use Cases

Areas:

finance

Additional Notes

Our method adapts LLaMA models to different domains such as biomedicine, finance, and law by transforming domain-specific corpora into reading comprehension tasks.

Training Details

Data Sources:

Open-Orca/OpenOrca, GAIR/lima, WizardLM/WizardLM_evol_instruct_V2_196k

Methodology:

Continued pre-training on domain-specific corpora and adaptation via reading comprehension transformation.

Release Notes

Version:

LLaMA-2-Chat-7B

Notes:

Released chat models developed from LLaMA-2-Chat-7B.

Version:

LLaMA-1-13B

Date:

12/19

Notes:

Released 13B base models developed from LLaMA-1-13B.

Version:

LLaMA-1-7B

Date:

9/18

Notes:

Released paper, code, data, and base models developed from LLaMA-1-7B.

LLM Name	AdaptLLM Finance Chat AWQ
Repository 🤗	https://huggingface.co/msamon/AdaptLLM-finance-chat-AWQ
Model Size	6.7b
Required VRAM	3.9 GB
Updated	2026-07-25
Maintainer	msamon
Model Type	llama
Instruction-Based	Yes
Model Files	3.9 GB
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32001
Torch Data Type	float16

Rank the AdaptLLM Finance Chat 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 AdaptLLM Finance Chat AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...epseek Coder 6.7B Instruct AWQ	16K / 3.9 GB	291702	19
Magicoder S DS 6.7B AWQ	16K / 3.9 GB	8	9
Law Chat AWQ	4K / 3.9 GB	7	4
Finance Chat AWQ	4K / 3.9 GB	7	3
Medicine Chat AWQ	4K / 3.9 GB	3	3
Medicine LLM AWQ	2K / 3.9 GB	6	4
Finance LLM AWQ	2K / 3.9 GB	12	5
AmberChat AWQ	2K / 3.9 GB	4	1
...LI LlumiX 32K Instruct F16 0.2	32K / 13.5 GB	8	1
...LI LlumiX 32K Instruct F16 0.1	32K / 13.5 GB	10	0

Note: green Score (e.g. "73.2") means that the model is better than msamon/AdaptLLM-finance-chat-AWQ.