LLM EXPLORER 68,292 MODELS INDEXED

Hy4 Flash MLX 3.1bit by nace-ai

By nace-ai · 434 downloads

Hy4 Flash MLX 3.1bit is an open-source language model by nace-ai. Features: 18.6b LLM, VRAM: 8GB, License: other, Quantized.

  2-bit   4-bit Base model:quantized:tencent/h...   Base model:tencent/hy4-flash   Conversational   Gguf   Hy4-flash   Hy v4 flash   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Hy4 Flash MLX 3.1bit Parameters and Internals

LLM NameHy4 Flash MLX 3.1bit
Repository πŸ€—https://huggingface.co/nace-ai/Hy4-flash-MLX-3.1bit 
Base Model(s)  tencent/Hy4-flash   tencent/Hy4-flash
Model Size18.6b
Required VRAM8 GB
Updated2026-11-22
Maintainernace-ai
Model Typehy_v4_flash
Model Files  35.6 GB   5.0 GB: 1-of-2   3.0 GB: 2-of-2   0.0 GB   0.0 GB   0.0 GB   0.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureHYV4FlashForConditionalGeneration
Licenseother
Transformers Version5.23.0