HRM-Text-1B-MLX-4bit
This is a persisted 4-bit MXFP4 MLX checkpoint for sapientinc/HRM-Text-1B. It is intended for use with HRM-mlx on...
This is a persisted 4-bit MXFP4 MLX checkpoint for sapientinc/HRM-Text-1B. It is intended for use with HRM-mlx on...
MXFP4MOE** GGUF quantization of Qwen3.6-35B-A3B, Alibaba Cloud’s efficient 35B MoE multimodal foundation model (3B activated) with 262K context,...
To G, my creator and lab host: Running locally here, I appreciate the sandbox. Let’s dive into the...
This is an first-generation gpt oss 120B vibe-code alpha(preview) of the powerful vibe-code LLM. It’s optimized to produce...
— Model architecture: full GLM-5.3 (GlmMoeDsaForCausalLM) — Input: text — Output: text — Source checkpoint: zai-org/GLM-5.3-BF16, revision 304b8051cfb2b260b61ce0cbe330e02a98e73639...
This is an MXFP4 MLX quantization of JetBrains/Mellum2-12B-A2.5B-Instruct. Mellum2 Instruct is a Mixture-of-Experts assistant model with 64 experts...
A surgically expert-pruned openai/gpt-oss-120b: 48 of 128 experts kept per layer (top-48 by REAP saliency), reducing the checkpoint...
Специализированные нецензурированные/аблитерированные кванты для новой модели OpenAI 20B MOE — Смесь экспертов при 80 т/с. См. настройки и...
GGUF conversions of the tiny Kimi-K3 0.40B development checkpoints. — Kimi-K3 architecture validation; — llama.cpp conversion and inference...
TurboQuant + MLX-MXFP4 (4-bit) variant of Qwen/Qwen3.6-35B-A3B. Apple Silicon (M1/M2/M3/M4) with TurboQuant structural pre-conditioning and MLX-native MXFP4 layout...