opencoder
8B parameters
Commercial OK

OpenCoder 8B

Fully-open coding model — training data + recipes published. Apache 2.0 with verifiable open-data lineage. The right pick for academic / reproducibility-sensitive work.

License: Apache 2.0·Released Nov 9, 2024·Context: 32,768 tokens

Overview

Fully-open coding model — training data + recipes published. Apache 2.0 with verifiable open-data lineage. The right pick for academic / reproducibility-sensitive work.

Strengths

  • Apache 2.0
  • Fully-open training data + recipes
  • Reproducibility-friendly

Weaknesses

  • Trails Qwen Coder on raw HumanEval

Quantization variants

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

QuantizationFile sizeVRAM required
Q4_K_M4.7 GB6 GB

Get the model

HuggingFace

Original weights

huggingface.co/infly/OpenCoder-8B-Instruct

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of OpenCoder 8B.

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.

Frequently asked

What's the minimum VRAM to run OpenCoder 8B?

6GB of VRAM is enough to run OpenCoder 8B at the Q4_K_M quantization (file size 4.7 GB). Higher-quality quantizations need more.

Can I use OpenCoder 8B commercially?

Yes — OpenCoder 8B ships under the Apache 2.0, which permits commercial use. Always read the license text before deployment.

What's the context length of OpenCoder 8B?

OpenCoder 8B supports a context window of 32,768 tokens (about 33K).

Source: huggingface.co/infly/OpenCoder-8B-Instruct

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