What are the hardware requirements for SUS Chat 34B GPTQ?

SUS Chat 34B GPTQ requires approximately 18.6 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 SUS Chat 34B GPTQ and how large is it?

SUS Chat 34B GPTQ is developed by TheBloke, a model with 34b 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 SUS Chat 34B GPTQ?

SUS Chat 34B GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SUS Chat 34B GPTQ by TheBloke — VRAM 18.6GB, 8K context

Name: SUS Chat 34B GPTQ
Author: TheBloke

SUS Chat 34B GPTQ is an open-source language model by TheBloke. Features: 34b LLM, VRAM: 18.6GB, Context: 8K, License: other, Quantized, LLM Explorer Score: 0.1.

4-bit Base model:quantized:sustech/s... Base model:sustech/sus-chat-34... Gptq Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/SUS-Chat-34B-GPTQ

SUS Chat 34B GPTQ Parameters and Internals

Model Type

text generation, dialogue

Use Cases

Areas:

Academic research, Commercial applications

Primary Use Cases:

Multilingual dialogue

Limitations:

Might produce unreasonable responses, Issues like hallucinations, non-determinism, and cumulative errors

Considerations:

Adjust generation configuration parameters for better downstream task performance.

Additional Notes

Demonstrates academic institutions can achieve high performance through instruction fine-tuning without increasing model size. Bridging academia and industry.

Supported Languages

Chinese (bilingual), English (bilingual)

Training Details

Data Sources:

multilingual instruction data

Methodology:

High-quality instruction fine-tuning; inter-instruction attention sharing for expanded window size.

Context Length:

8000

Input Output

Input Format:

SUS ### Human: {prompt} ### Assistant:

Accepted Modalities:

text

Output Format:

Text response

Performance Tips:

Adjust generation configuration parameters for specific downstream tasks.

LLM Name	SUS Chat 34B GPTQ
Repository 🤗	https://huggingface.co/TheBloke/SUS-Chat-34B-GPTQ
Model Name	SUS Chat 34B
Model Creator	Southern university of science and technology
Base Model(s)	SUS Chat 34B SUSTech/SUS-Chat-34B
Model Size	34b
Required VRAM	18.6 GB
Updated	2026-07-28
Maintainer	TheBloke
Model Type	llama
Model Files	18.6 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Rank the SUS Chat 34B GPTQ 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 SUS Chat 34B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
Smaug 34B V0.1 GPTQ	195K / 21.2 GB	1	1
Yi 34B 200K RPMerge GPTQ	195K / 21.2 GB	2	4
Tess 34B V1.5B GPTQ	195K / 18.6 GB	18	8
...4B 200K DARE Megamerge V8 GPTQ	195K / 18.6 GB	4	3
...y 34B 200K Chat Evaluator GPTQ	195K / 18.6 GB	8	3
Deepmoney 34B 200K Base GPTQ	195K / 18.6 GB	3	3
...ous Capybara Limarpv3 34B GPTQ	195K / 18.6 GB	11	4
Bagel 34B V0.2 GPTQ	195K / 18.6 GB	7	2
Bagel DPO 34B V0.2 GPTQ	195K / 18.6 GB	5	2
Nontoxic Bagel 34B V0.2 GPTQ	195K / 18.6 GB	3	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/SUS-Chat-34B-GPTQ.