DeepSeek-V4-Flash-0731-REAP-150b-TQ3_4S-GGUF
A custom, selectively-quantized GGUF of the DeepSeek-V4-Flash-0731 architecture, pruned to the 150B «REAP» variant, quantized with a hand-tuned...
A custom, selectively-quantized GGUF of the DeepSeek-V4-Flash-0731 architecture, pruned to the 150B «REAP» variant, quantized with a hand-tuned...
This is an uncensored version of deepseek-ai/DeepSeek-V4-Flash-0731 created with abliteration (see remove-refusals-with-transformers to know more about it). This...
Утяжелители MXFP4-MLX без цензуры /стирания для официального DeepSeek-V4-Flash-0731, с головками DSpark MTP, хранящимися на складе, для одной Mac...
Извините, ребята, если информация неверна — я просто был слишком ленив, чтобы все это выписать (T_T) Модальности:Генерация текста...
An abliterated (refusal-ablated) build of deepseek-ai/DeepSeek-V4-Flash-0731. Produced by a forward-only, closed-form weight edit — no training, no fine-tuning,...
An 8-bit (UD-Q8KXL) GGUF conversion of DeepSeek-V4-Flash-0731 with a mode-merged abliteration overlay applied to the attention output projections....
AWQ-calibrated mixed-precision quantization of DeepSeek-V4-Flash-0731 (304B MoE, 43 layers, 256 routed experts/layer, Hyper-Connections, HISA attention) for Apple Silicon...
> Work in progress. This card and the checkpoint are still being validated. Routed experts of DeepSeek-V4-Flash-0731 transcoded...
Ablation-guided ‘heterogeneous’ GGUF quantization of DeepSeek-V4-Flash-0731. 95.8 GB single file. Fits 128 GB memory, leaving ~32 GB for...
DeepSeek-V4-Flash-0731 compressed from 155.42 GiB to 91.93 GiB (1.69×) so it fits and serves on ONE NVIDIA DGX...