No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from unsloth/DeepSeek-V4-Pro-0813-GGUF
All models by unsloth →Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.
Quants are uploaded to this repository as they finish converting.
DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached.
DeepSeek-V4-Pro-0813 outperforms DeepSeek-V4-Pro (Preview) on the benchmarks listed below, and is broadly competitive with the strongest proprietary models available.
Notes:
max reasoning effort level with temperature = 1.0, top_p = 0.95.This release does not include a Jinja-format chat template. Instead, we provide a dedicated encoding folder with Python scripts and test cases demonstrating how to encode messages in OpenAI-compatible format into input strings for the model, and how to parse the model's text output. Please refer to the encoding [blocked] folder for full documentation.
The reasoning_effort parameter now supports three levels — low, high, and max — which control how much deliberation the model spends before answering.
A brief example:
This repository and the model weights are licensed under the MIT License [blocked].
If you have any questions, please raise an issue or contact us at service@deepseek.com [blocked].
from encoding_dsv4 import encode_messages, parse_message_from_completion_text
messages = [ {"role": "user", "content": "hello"}, {"role": "assistant", "content": "Hello! I am DeepSeek.", "reasoning_content": "thinking..."}, {"role": "user", "content": "1+1=?"}]
# messages -> stringprompt = encode_messages(messages, thinking_mode="thinking", reasoning_effort="max")
# string -> tokensimport transformerstokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Pro-0813")tokens = tokenizer.encode(prompt)@misc{deepseekai2026deepseekv4, title={DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence}, author={DeepSeek-AI}, year={2026},}