Stable DiffCoder 8B Base is an open-source language model by ByteDance-Seed. Features: 8b LLM, VRAM: 16.5GB, Context: 8K, License: mit, LLM Explorer Score: 0.28.
Arxiv:2601.15892 Custom code Endpoints compatible Feature-extraction Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ByteDance-Seed/Stable-DiffCoder-8B-Base
Stable DiffCoder 8B Base Benchmarks
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)
Stable DiffCoder 8B Base Parameters and Internals
| LLM Name | Stable DiffCoder 8B Base |
| Repository 🤗 | https://huggingface.co/ByteDance-Seed/Stable-DiffCoder-8B-Base |
| Model Size | 8b |
| Required VRAM | 16.5 GB |
| Updated | 2026-03-31 |
| Maintainer | ByteDance-Seed |
| Model Type | llama |
| Model Files | |
| Model Architecture | StableDiffcoderForCausalLM |
| License | mit |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 5.3.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <[PAD▁TOKEN]> |
| Vocabulary Size | 155136 |
| Torch Data Type | bfloat16 |
Rank the Stable DiffCoder 8B Base Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52392 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a