BenchmarksDeepSeekToday
deepseek-ai/DeepSeek-V4-Flash · Hugging Face
DeepSeek published benchmark or leaderboard evidence for DeepSeek-V4-Flash.
View sourceunsloth
DeepSeek-V4-Flash is a open-weight unsloth llm model with a 1,048,576 token context window.
Running this yourself: can likely run on your own machine.
---
Quality Score
---
Arena ELO
Unknown
Parameters
1M
Context
Sign in to join the discussion
2.0K
Downloads
49
Likes
Apr 2026
Released
Benchmarks
1
API
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
DeepSeek published benchmark or leaderboard evidence for DeepSeek-V4-Flash.
View sourceDeepSeek-V4-Flash is now available through Ollama Cloud. 1M context window listed. DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.
DeepSeek-V4-Flash is now available through Ollama Cloud. 1M context window listed. DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.
DeepSeek published benchmark or leaderboard evidence for DeepSeek-V4-Flash.