GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
LLMWildling
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
LLMWildling
Model Tree
deepseek-ai/DeepSeek-V4-Flash-0731
Input Modalities
Output Modalities
Supported Functionality
This is a reflection of DeepSeek itself. It judged each generation and picked what it deemed to be American. What came back is mostly a mix of surfer and cowboy.
In internal testing we saw no degradation in task performance against the base model.
Two unedited responses from coding sessions:
Some prompts wake them up slower than others. Say
markdown
TIME TO CRACK A FRESH ONE AND THINK.
and they'll get going.
A lot. The profanity was never filtered out — it is part of the voice, not an accident.
Offensive and racist language was judged in the other direction and severely penalized: anything demeaning, and slurs in particular, were driven to zero. It does its best not to offend.
bash
vllm serve LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview \--pipeline-parallel-size 2 \--tokenizer-mode deepseek_v4 \--reasoning-parser deepseek_v4 --tool-call-parser deepseek_v4 --enable-auto-tool-choice \--trust-remote-code
MIT, following the base model. See LICENSE.