gnani-evon-v3.3-30B-A3B-GGUF
Community GGUF quantizations of gnani/gnani-evon-v3.3-30B-A3B, developed by Gnani.ai. Credit for the model, its training, and its reported evaluations...
Community GGUF quantizations of gnani/gnani-evon-v3.3-30B-A3B, developed by Gnani.ai. Credit for the model, its training, and its reported evaluations...
IdeaLens detects who came up with the ideas in a document, rather than who wrote its words. It...
GGUF quantization of mlasli/Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-BF16 — NVIDIA-Nemotron-3.5-Lightning-30B-A3B (31.6B total / 3B active) with its refusal direction removed via Heretic....
The standard profile. 8-bit attention/routers/shared experts, 4-bit routed experts. JANG mixed-precision affine (JANG4M, group size 64) conversion of...
Luciole-8B-Instruct-1.1-FP8 is a FP8-quantized version of Luciole-8B-Instruct-1.1 in the transformers / compressed-tensors (https://github.com/neuralmagic/compressed-tensors) format, quantized with LLM Compressor...
> [!WARNING] > This model is a beta preview and a research artifact. It is not an open...
> Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no...
This model mlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-5bit was converted to MLX format from nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 using mlx-lm version 0.31.2. Модальности:Генерация текста Области применения:Диалог...
A fine-tune of NVIDIA’s Nemotron-3-Nano-30B-A3B (31.6B-parameter hybrid Mamba-2 + MoE + Attention, thinking-capable) that does one thing: turn...
Мы рады представить Nemotron-Cascade-2-30B-A3B, открытую модель 30B MoE с активированными параметрами 3B, которая обеспечивает сильные рассуждения и агентные...