What are the hardware requirements for DeepSeek Coder V2 Lite Instruct AWQ?

DeepSeek Coder V2 Lite Instruct AWQ requires approximately 9.1 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 Coder V2 Lite Instruct AWQ and how large is it?

DeepSeek Coder V2 Lite Instruct AWQ is developed by TechxGenus, a model with 15.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does DeepSeek Coder V2 Lite Instruct AWQ perform on standard benchmarks?

DeepSeek Coder V2 Lite Instruct AWQ has the following published scores: LMSYS ELO 1264. Compare against reference models on this page or on the LLM Explorer leaderboards.

DeepSeek Coder V2 Lite Instruct AWQ by TechxGenus — VRAM 9.1GB, 160K context

Name: DeepSeek Coder V2 Lite Instruct AWQ
Author: TechxGenus

DeepSeek Coder V2 Lite Instruct AWQ is an open-source language model by TechxGenus. Features: 15.7b LLM, VRAM: 9.1GB, Context: 160K, License: other, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.29, ELO: 1264.

Arxiv:2401.06066 4-bit Awq Codegen Conversational Custom code Deepseek v2 Endpoints compatible Instruct Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ

DeepSeek Coder V2 Lite Instruct AWQ Benchmarks

LMSys ELO 1264 vs 1272 (so35) -0.6%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

DeepSeek Coder V2 Lite Instruct AWQ Parameters and Internals

Model Type

Mixture-of-Experts (MoE) code language model

Use Cases

Areas:

code intelligence, mathematical reasoning

Primary Use Cases:

coding tasks, general language tasks

Additional Notes

AWQ quantized version available for DeepSeek-Coder-V2-Lite-Instruct model.

Supported Languages

number_of_languages (,), languages_typical_comments (Expands its support for programming languages from 86 to 338.)

Training Details

Data Sources:

high-quality, multi-source corpus

Data Volume:

6 trillion tokens

Methodology:

Mixture of Experts (MoE) approach

Context Length:

128000

Model Architecture:

Mixture-of-Experts (MoE)

Input Output

Input Format:

Chat completion and code completion

Accepted Modalities:

text

Output Format:

Generated code

LLM Name	DeepSeek Coder V2 Lite Instruct AWQ
Repository 🤗	https://huggingface.co/TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ
Model Size	15.7b
Required VRAM	9.1 GB
Updated	2026-07-24
Maintainer	TechxGenus
Model Type	deepseek_v2
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 4.1 GB: 2-of-2
AWQ Quantization	Yes
Quantization Type	awq
Generates Code	Yes
Model Architecture	DeepseekV2ForCausalLM
License	other
Context Length	163840
Model Max Length	163840
Transformers Version	4.41.2
Tokenizer Class	LlamaTokenizer
Padding Token	<｜end▁of▁sentence｜>
Vocabulary Size	102400
Torch Data Type	float16

Rank the DeepSeek Coder V2 Lite 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 V2 Lite Instruct AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...eepSeek Coder V2 Lite Instruct	160K / 31.4 GB	542062	628
...2 Lite Instruct FlashAttnPatch	160K / 31.4 GB	24	0

Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ.