What are the hardware requirements for DeepSeek V3.1 AWQ?

DeepSeek V3.1 AWQ requires approximately 119.9 GB of VRAM and supports a context window of 160K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DeepSeek V3.1 AWQ and how large is it?

DeepSeek V3.1 AWQ is developed by QuantTrio, a model with 684.5b 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 DeepSeek V3.1 AWQ?

DeepSeek V3.1 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DeepSeek V3.1 AWQ by QuantTrio — VRAM 119.9GB, 160K context

Name: DeepSeek V3.1 AWQ
Author: QuantTrio

DeepSeek V3.1 AWQ is an open-source language model by QuantTrio. Features: 684.5b LLM, VRAM: 119.9GB, Context: 160K, License: mit, Quantized, LLM Explorer Score: 0.2.

Arxiv:2412.19437 4-bit Awq Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Conversational Custom code Deepseek v3 En Endpoints compatible Gptq Quantized Region:us Safetensors Sharded Tensorflow Vllm Zh

Model Card on HF 🤗: https://huggingface.co/QuantTrio/DeepSeek-V3.1-AWQ

DeepSeek V3.1 AWQ Parameters and Internals

LLM Name	DeepSeek V3.1 AWQ
Repository 🤗	https://huggingface.co/QuantTrio/DeepSeek-V3.1-AWQ
Base Model(s)	deepseek-ai/DeepSeek-V3.1 deepseek-ai/DeepSeek-V3.1
Model Size	684.5b
Required VRAM	119.9 GB
Updated	2026-07-23
Maintainer	QuantTrio
Model Type	deepseek_v3
Model Files	2.9 GB: 1-of-134 3.0 GB: 2-of-134 3.0 GB: 3-of-134 3.0 GB: 4-of-134 3.0 GB: 5-of-134 3.0 GB: 6-of-134 3.0 GB: 7-of-134 3.0 GB: 8-of-134 3.0 GB: 9-of-134 3.0 GB: 10-of-134 3.0 GB: 11-of-134 3.0 GB: 12-of-134 3.0 GB: 13-of-134 3.0 GB: 14-of-134 3.0 GB: 15-of-134 3.0 GB: 16-of-134 3.0 GB: 17-of-134 3.0 GB: 18-of-134 3.0 GB: 19-of-134 3.0 GB: 20-of-134 3.0 GB: 21-of-134 3.0 GB: 22-of-134 3.0 GB: 23-of-134 3.0 GB: 24-of-134 3.0 GB: 25-of-134 3.0 GB: 26-of-134 3.0 GB: 27-of-134 3.0 GB: 28-of-134 3.0 GB: 29-of-134 3.0 GB: 30-of-134 3.0 GB: 31-of-134 3.0 GB: 32-of-134 3.0 GB: 33-of-134 3.0 GB: 34-of-134 3.0 GB: 35-of-134 3.0 GB: 36-of-134 3.0 GB: 37-of-134 3.0 GB: 38-of-134 3.0 GB: 39-of-134 3.0 GB: 40-of-134
Supported Languages	zh en
GPTQ Quantization	Yes
AWQ Quantization	Yes
Quantization Type	gptq\|awq
Model Architecture	DeepseekV3ForCausalLM
License	mit
Context Length	163840
Model Max Length	163840
Transformers Version	4.44.2
Vocabulary Size	129280
Torch Data Type	bfloat16

Rank the DeepSeek V3.1 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 DeepSeek V3.1 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
DeepSeek R1 0528	160K / 180.4 GB	244573	2457
DeepSeek V3	160K / 171.8 GB	1155192	4102
DeepSeek R1	160K / 180.4 GB	8739585	13461
DeepSeek V3 Base	160K / 171.8 GB	34207	1700
DeepSeek V3.0324	160K / 184.7 GB	835522	3148
DeepSeek V3	160K / 171.8 GB	20952	13
DeepSeek V3.1 Terminus	160K / 171.8 GB	15	4
DeepSeek V3.1	160K / 176.1 GB	16	3
DeepSeek V3.1	160K / 180.4 GB	307929	826
DeepSeek R1 Block INT8	160K / 176.1 GB	171	50

Note: green Score (e.g. "73.2") means that the model is better than QuantTrio/DeepSeek-V3.1-AWQ.