No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from deepseek-ai/DeepSeek-V4-Pro-DSpark
All models by deepseek-ai →
Note: DeepSeek-V4-Pro-DSpark is not a new model. It is the same checkpoint with an additional speculative decoding module attached. A minimal inference example is available in the inference [blocked] folder. For more details, refer to: https://github.com/deepseek-ai/DeepSpec
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.
DeepSeek-V4 series incorporate several key upgrades in architecture and optimization:
We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline. The post-training features a two-stage paradigm: independent cultivation of domain-specific experts (through SFT and RL with GRPO), followed by unified model consolidation via on-policy distillation, integrating distinct proficiencies across diverse domains into a single model.
DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, significantly advances the knowledge capabilities of open-source models, firmly establishing itself as the best open-source model available today. It achieves top-tier performance in coding benchmarks and significantly bridges the gap with leading closed-source models on reasoning and agentic tasks. Meanwhile, DeepSeek-V4-Flash-Max achieves comparable reasoning performance to the Pro version when given a larger thinking budget, though its smaller parameter scale naturally places it slightly behind on pure knowledge tasks and the most complex agentic workflows.
*FP4 + FP8 Mixed: MoE expert parameters use FP4 precision; most other parameters use FP8.
DeepSeek-V4-Pro and DeepSeek-V4-Flash both support three reasoning effort modes:
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.
A brief example:
DSpark speculative decoding is enabled with a single flag — add --speculative-config with method: dspark to your vLLM launch command:
--speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'
For example, the command below serves the model with vLLM on a single 4×GB300 node. See the vLLM recipe for detailed instructions and other hardware configurations.
Please refer to the inference [blocked] folder for detailed instructions on running DeepSeek-V4 locally, including model weight conversion and interactive chat demos.
For local deployment, we recommend setting the sampling parameters to temperature = 1.0, top_p = 1.0. For the Think Max reasoning mode, we recommend setting the context window to at least 384K tokens.
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")
# string -> tokensimport transformerstokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Pro")tokens = tokenizer.encode(prompt)vllm serve deepseek-ai/DeepSeek-V4-Pro-DSpark \ --trust-remote-code --kv-cache-dtype fp8 --block-size 256 \ --data-parallel-size 4 --enable-expert-parallel \ --moe-backend deep_gemm_mega_moe \ --attention-config '{"use_fp4_indexer_cache": true}' \ --compilation-config '{"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}' \ --speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'@misc{deepseekai2026deepseekv4, title={DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence}, author={DeepSeek-AI}, year={2026},}