Hy3-REAP-200B-21B
A 33%-expert-pruned version of Tencent Hunyuan Hy3 (295B / A21B), compressed with REAP (Router-weighted Expert Activation Pruning) —...
A 33%-expert-pruned version of Tencent Hunyuan Hy3 (295B / A21B), compressed with REAP (Router-weighted Expert Activation Pruning) —...
Non-uniform expert prune · NVFP4 · runs on FOUR Blackwell cards · verified 0-refusal Three transformations in one...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
weighted/imatrix quants of https://huggingface.co/hotdogs/Qwen35B-Agent-R2 For a convenient overview and download list, visit our model page for this model....
Quantized tencent/Hy3 for Apple Silicon MLX / JANG runtimes — a 295B-total / 21B-active text MoE, packed to...
High-quality imatrix GGUF quantizations of tencent/Hy3, Tencent’s 295B-parameter Mixture-of-Experts model with ~21B active parameters per token. Produced with...
QLoRA fine-tune of NVIDIA Nemotron-3-Super-120B-A12B (120B-total / 12B-active hybrid Mamba-2 + Latent-MoE, nemotronh) on the piagent split of...
QLoRA fine-tune of NVIDIA Nemotron-3-Super-120B-A12B (120B-total / 12B-active hybrid Mamba-2 + Latent-MoE, nemotronh) on the piagent split of...
MobileMoE — это семейство языковых моделей Mixture-of-Experts (MoE) на устройстве с субмиллиардными активными параметрами, предназначенных для продвижения границы...
LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2 [Stage 2] Fine tune of «LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P» using Unsloth using custom dataset(s), 128k context in 16 bit precision....