A Totally UNCENSORED Deepseek v4 FLASH and it is runs on DSPARK so it keeps the 50-60 tok/s simple model swap - GitHub - tonyd2wild/DeepSeek-v4-Flash-DSpark-Abliterated-Uncensored-2x-DGX-Spark: Keys/drowzeys' abliterated (uncensored) DeepSeek-V4-Flash-DSpark served on 2x DGX Spark TP=2. Fork of the DS4 DSpark recipe with the model swapped in. Full model credit: Keys/drowzeys. · GitHub
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Request for deepseek v4 flash/pro API Rate Limit Increase (RPH) For light use, Academic and small entertainment | 0 | 252 | June 2, 2026 | |
| deepseek-ai/DeepSeek-V4-Flash-0731 | 0 | 546 | July 31, 2026 | |
| Apply for Public API Endpoints permission | 0 | 24 | July 25, 2026 | |
| DeepSeek V3.2 API returns 404 error today after yesterday's work | 0 | 359 | December 28, 2025 | |
| Issues on deepseek models, | 1 | 219 | November 14, 2025 | |
| DEEP SEEK v4 Pro GPU SUPPORT | 2 | 708 | July 18, 2026 | |
| Deepseek v4 flash 0731 (ai index = 50) ~ GLM 5.2 (ai index = 51) - open weights are already available :-) | 17 | 3038 | August 3, 2026 | |
| Please add more deepseek models and fix a issue that exists with deepseek 3.2 | 1 | 221 | April 17, 2026 | |
| Request to enable Public API Endpoints for my account | 0 | 39 | July 8, 2026 | |
| Request for deepseek-v4-pro API Rate Limit Increase | 3 | 447 | June 26, 2026 |