ChatBerry
!https://i.pinimg.com/736x/bd/b9/be/bdb9bef25d336c9887e351cd1d7bfd57.jpg ChatBerry is the flagship release of the ChatBerry family — a fine-tuned version of artindnr/strawberry-1, converted from...
!https://i.pinimg.com/736x/bd/b9/be/bdb9bef25d336c9887e351cd1d7bfd57.jpg ChatBerry is the flagship release of the ChatBerry family — a fine-tuned version of artindnr/strawberry-1, converted from...
Private OpenMed development export of deepgrove/maple-preview revision ac1ddd79d2b5cb4406f5d2bebdf95406ce505a07 for a compatible ONNX Runtime Web/WebGPU integration. The expert matrices...
Private OpenMed development export of deepgrove/maple-preview for MLX. It was converted from source revision ac1ddd79d2b5cb4406f5d2bebdf95406ce505a07 with 8-bit affine...
For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available...
A GGUF quant of 0xSero/DeepSeek-V4-Flash-0731-REAP, the K160 expert-pruned checkpoint of deepseek-ai/DeepSeek-V4-Flash-0731. The pruning is 0xSero’s work: 160 of...
> 4-bit NF4 quantized version of fuse-1 Lite. 3.36 GB VRAM — runs on T4, RTX 3060, and...
!from [pinterest](https://i.pinimg.com/736x/b5/04/41/b50441f456e162ee3fb651898d20324a.jpg) Strawberry-1 is a fine-tuned version of openai/gpt-oss-20b, trained to produce high-quality Farsi (Persian) reasoning traces and...
DeepSeek-V4-Flash-0731 compressed from 155.42 GiB to 91.93 GiB (1.69×) so it fits and serves on ONE NVIDIA DGX...
Экспериментальный исследовательский артефакт И кандидат НА высвобождение. Это гибридная контрольная точка MLX, а не полностью тройная сквозная модель....
A 30.5B-parameter Mixture-of-Experts reasoning model built from Qwen3-30B-A3B through a single CoT-preserving BF16 LoRA pass. Satella is the...