tensorblock/winglian_seed-coder-triton-8b-v1-GGUF

winglian/seed-coder-triton-8b-v1 - GGUF

Join our Discord to learn more about what we're building ↗

This repo contains GGUF format model files for winglian/seed-coder-triton-8b-v1.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

<[begin▁of▁sentence]><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Model file specification

Filename	Quant type	File Size	Description
seed-coder-triton-8b-v1-Q2_K.gguf	Q2_K	3.304 GB	smallest, significant quality loss - not recommended for most purposes
seed-coder-triton-8b-v1-Q3_K_S.gguf	Q3_K_S	3.801 GB	very small, high quality loss
seed-coder-triton-8b-v1-Q3_K_M.gguf	Q3_K_M	4.155 GB	very small, high quality loss
seed-coder-triton-8b-v1-Q3_K_L.gguf	Q3_K_L	4.458 GB	small, substantial quality loss
seed-coder-triton-8b-v1-Q4_0.gguf	Q4_0	4.812 GB	legacy; small, very high quality loss - prefer using Q3_K_M
seed-coder-triton-8b-v1-Q4_K_S.gguf	Q4_K_S	4.843 GB	small, greater quality loss
seed-coder-triton-8b-v1-Q4_K_M.gguf	Q4_K_M	5.071 GB	medium, balanced quality - recommended
seed-coder-triton-8b-v1-Q5_0.gguf	Q5_0	5.764 GB	legacy; medium, balanced quality - prefer using Q4_K_M
seed-coder-triton-8b-v1-Q5_K_S.gguf	Q5_K_S	5.764 GB	large, low quality loss - recommended
seed-coder-triton-8b-v1-Q5_K_M.gguf	Q5_K_M	5.897 GB	large, very low quality loss - recommended
seed-coder-triton-8b-v1-Q6_K.gguf	Q6_K	6.775 GB	very large, extremely low quality loss
seed-coder-triton-8b-v1-Q8_0.gguf	Q8_0	8.773 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/winglian_seed-coder-triton-8b-v1-GGUF --include "seed-coder-triton-8b-v1-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/winglian_seed-coder-triton-8b-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'