GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
wrldsuksgo2mars
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
wrldsuksgo2mars
Model Tree
deepseek-ai/DeepSeek-V4-Pro-0813
Input Modalities
Output Modalities
Supported Functionality
The encoder replayed a frozen, deterministic 1,426-prompt corpus containing about 1.081 million English-, Chinese-, code-, reasoning-, instruction-, and structured-output-focused tokens through the real learned routers. Naturally under-covered experts were augmented deterministically from router ranks 7–12 to a 1,024-row target, with the declared isotropic recovery residual used only when that natural tail was exhausted. Each dSpark block used a deterministic 327,680-anchor sample of the same activation stream.
The run was streamed layer by layer with bounded two-RTX Hessians, resumable batch capture/replay, per-projection numerical validation, and a retained per-layer/expert error and coverage ledger. No Spark compute was used during quantization.
The final checkpoint passed its complete tensor/shape/digest contract and was
served on the current DS4RT AFD engine:
one RTX PRO 6000 Blackwell coordinator on a 400-Gb/s link plus four DGX Spark
TP4 expert ranks, using balanced FP8 KV and adaptive dSpark.
| Current-head gate | Result |
|---|---|
| Tool Eval Bench, all 69 scenarios, no thinking | 81/100 (112/138 points) |
| GLMRT-style seven-case blended decode | 39.84 tok/s |
| Code slice of the same decode blend | 51.01 tok/s |
| Fresh 8K prefill, C1 median over three | 739.9 tok/s |
| Adaptive dSpark acceptance | 3,809/5,759 (66.14%) |
The complete 27-cell C1/C2/C4 throughput matrix and all validation requests finished without a serving failure. The 8K result used 8,221 fresh prefill rows; all three samples completed full attention with zero runtime captures.
The original model card follows for architecture, prompting, benchmark, and license information. Its native-weight vLLM/SGLang launch examples are not EXL3 serving instructions for this checkpoint.
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.
| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Pro (Preview) | DeepSeek-V4-Flash (Preview) | GLM-5.2 | Kimi K3 | Opus-4.8 | Fable-5 (w/ fallback) |
|---|---|---|---|---|---|---|---|---|
| HLE (wo / w tools) | 42.7 / 60.0 | 37.8 / 51.5 | 37.7 / 48.2 | 34.8 / 45.1 | 40.5 / 54.7 | 43.5 / 56.0 | 49.8 / 57.9 | 53.3 / 63.0 |
| Terminal Bench 2.1 |
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 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:
python
from encoding_dsv4 import encode_messages, parse_message_from_completion_textmessages = [{"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)
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.
bash
vllm serve deepseek-ai/DeepSeek-V4-Pro-0813 \--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}' \--speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'
Enable DSpark with --speculative-algorithm DSPARK and do not set a separate --speculative-draft-model-path as the target and draft weights therefore come from the same checkpoint.
See the SGLang cookbook for detailed instructions, benchmarks and other hardwares configurations.
bash
sglang serve \--trust-remote-code \--model-path deepseek-ai/DeepSeek-V4-Pro-0813 \--tp 4 \--moe-runner-backend flashinfer_mxfp4 \--speculative-algorithm DSPARK \--mem-fraction-static 0.90 \--chunked-prefill-size 4096 \--swa-full-tokens-ratio 0.1 \
Please refer to the inference 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, with top_p = 0.95 for agentic scenarios and top_p = 1.0 otherwise. For the high and max reasoning effort levels, we recommend a maximum output length of 384K tokens.
This repository and the model weights are licensed under the MIT License.
markdown
@misc{deepseekai2026deepseekv4,title={DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence},author={DeepSeek-AI},year={2026},}
If you have any questions, please raise an issue or contact us at service@deepseek.com.
| 87.9 |
| 82.7 |
| 72.1 |
| 61.8 |
| 81.0 |
| 88.3 |
| 85.0 |
| 88.0 |
| NL2Repo | 61.5 | 54.2 | 38.5 | 39.4 | 48.9 | - | 69.7 | - |
| Cybergym | 83.3 | 76.7 | 52.7 | 38.7 | - | 80.0 | 78.3 | 83.1 |
| DeepSWE | 62.7 | 54.4 | 12.8 | 7.3 | 46.2 | 67.5 | 58.0 | 70.0 |
| Toolathlon-Verified | 74.1 | 70.3 | 55.9 | 49.7 | 59.9 | 76.5 | 76.2 | 77.9 |
| Agents' Last Exam | 25.7 | 25.2 | 16.5 | 15.8 | 23.8 | 27.6 | 25.7 | - |
| AutomationBench (Public) | 31.8 | 25.1 | 12.8 | 10.8 | 12.9 | 30.8 | 27.2 | 29.1 |
| DSBench-FullStack † | 71.1 | 68.7 | 41.8 | 37.0 | 61.8 | 73.7 | 71.6 | 77.2 |
| DSBench-Hard † | 67.2 | 59.6 | 31.1 | 25.8 | 54.5 | 63.0 | 71.7 | 68.3 |