What are the hardware requirements for Deepseek Coder 33B Instruct AWQ?

Deepseek Coder 33B Instruct AWQ requires approximately 18.1 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Coder 33B Instruct AWQ and how large is it?

Deepseek Coder 33B Instruct AWQ is developed by TheBloke, a model with 33b 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 Coder 33B Instruct AWQ?

Deepseek Coder 33B Instruct AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Deepseek Coder 33B Instruct AWQ by TheBloke — VRAM 18.1GB, 16K context

Name: Deepseek Coder 33B Instruct AWQ
Author: TheBloke

Deepseek Coder 33B Instruct AWQ is an open-source language model by TheBloke. Features: 33b LLM, VRAM: 18.1GB, Context: 16K, License: other, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.1.

4-bit Awq Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Codegen Conversational Deploy:azure Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheBloke/deepseek-coder-33B-instruct-AWQ

Deepseek Coder 33B Instruct AWQ Parameters and Internals

Model Type

deepseek

Supported Languages

English (high), Chinese (high)

Training Details

Data Sources:

project-level code corpus

Data Volume:

2T tokens

Methodology:

pre-trained with a window size of 16K and a fill-in-the-blank task

Context Length:

16000

LLM Name	Deepseek Coder 33B Instruct AWQ
Repository 🤗	https://huggingface.co/TheBloke/deepseek-coder-33B-instruct-AWQ
Model Name	Deepseek Coder 33B Instruct
Model Creator	DeepSeek
Base Model(s)	Deepseek Coder 33B Instruct deepseek-ai/deepseek-coder-33b-instruct
Model Size	33b
Required VRAM	18.1 GB
Updated	2026-08-02
Maintainer	TheBloke
Model Type	deepseek
Instruction-Based	Yes
Model Files	10.0 GB: 1-of-2 8.1 GB: 2-of-2
AWQ Quantization	Yes
Quantization Type	awq
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	4.35.0
Tokenizer Class	LlamaTokenizerFast
Beginning of Sentence Token	<｜begin▁of▁sentence｜>
End of Sentence Token	<\|EOT\|>
Vocabulary Size	32256
Torch Data Type	float16

Rank the Deepseek Coder 33B Instruct 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 Coder 33B Instruct AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...er 33B Instruct 4.0bpw H6 EXL2	16K / 17.1 GB	5	5
...er 33B Instruct 8.0bpw H8 EXL2	16K / 33.6 GB	6	3
...er 33B Instruct 3.0bpw H6 EXL2	16K / 13 GB	10	1
...r 33B Instruct 4.65bpw H6 EXL2	16K / 19.8 GB	6	1
...er 33B Instruct 5.0bpw H6 EXL2	16K / 21.2 GB	5	1
Deepseek Wizard 33B Slerp	16K / 35.3 GB	7	0
ValidateAI 3 33B Ties	16K / 66.5 GB	7	0
ValidateAI 2 33B AT	16K / 66.5 GB	6	0
Deepseek Coder 33B Instruct	16K / 66.5 GB	3376	580
...epseek Coder 33B Instruct GPTQ	16K / 17.4 GB	267	25

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-33B-instruct-AWQ.