deepseek

33B parameters

Commercial OK

DeepSeek Coder V3

DeepSeek's coder line successor. Dense 33B; competitive with Qwen 2.5 Coder 32B on SWE-Bench.

License: DeepSeek License·Released Feb 8, 2026·Context: 131,072 tokens

Overview

DeepSeek's coder line successor. Dense 33B; competitive with Qwen 2.5 Coder 32B on SWE-Bench.

Family & lineage

How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.

Parent / base model

DeepSeek Coder V2 Lite (16B)16B

Consumer

Family siblings (deepseek-coder)

DeepSeek Coder V2 Lite (16B)16B

Consumer

DeepSeek Coder V333B

You are here

DeepSeek Coder V2 236B236B

Datacenter

Strengths

Strong on multi-file editing
DeepSeek code lineage

Weaknesses

DeepSeek License vs Apache 2.0 of Qwen

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

Quantization	File size	VRAM required
AWQ-INT4	19.0 GB	22 GB

Get the model

HuggingFace

Original weights

huggingface.co/deepseek-ai/DeepSeek-Coder-V3-33B

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of DeepSeek Coder V3.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Same tier

Models in the same parameter band as this one

Step up

More capable — bigger memory footprint

Step down

Smaller — faster, runs on weaker hardware

Frequently asked

What's the minimum VRAM to run DeepSeek Coder V3?

22GB of VRAM is enough to run DeepSeek Coder V3 at the AWQ-INT4 quantization (file size 19.0 GB). Higher-quality quantizations need more.

Can I use DeepSeek Coder V3 commercially?

Yes — DeepSeek Coder V3 ships under the DeepSeek License, which permits commercial use. Always read the license text before deployment.

What's the context length of DeepSeek Coder V3?

DeepSeek Coder V3 supports a context window of 131,072 tokens (about 131K).

Source: huggingface.co/deepseek-ai/DeepSeek-Coder-V3-33B

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.