dealign.ai(@dealignai):DeepSeek-V4-Flash CRACK'd (ablated/uncensored) - Mac's Only (Osaurus/vMLX) https://t.co/w6MzqDI5vF 100gb, 20token/s. JANGTQ ~85gb will be out shortly. This model has taught me so much. Most importantly, to actually read research papers that frontierlabs release 😅 Keep in mind the MMLU is honestly just for comparison to base (using logit answering, instruct mode for sake of speed) I went out of my way to make sure it has no issues with code formatting/syntax/etcetc. Max reasoning mode works.

2026.05.24 07:53

DeepSeek-V4-Flash CRACK'd (ablated/uncensored) - Mac's Only (Osaurus/vMLX) 100gb, 20token/s. JANGTQ ~85gb will be out shortly. This model has taught me so much. Most importantly, to actually read research papers that frontierlabs release 😅 Keep in mind the MMLU is honestly just for comparison to base (using logit answering, instruct mode for sake of speed) I went out of my way to make sure it has no issues with code formatting/syntax/etcetc. Max reasoning mode works.