Downloads · 30 days
27
7% of all-time downloads
IHaveNoClueAndIMustPost/Qwen3.6-27B-smol-MTP-IQ4_NL.gguf
Qwen3.6-27B-smol-MTP-IQ4_NL.gguf is a machine learning model from IHaveNoClueAndIMustPost. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Qwen3.6-27B-smol-MTP-IQ4NL from ubergarm with grafted MTP/draft tensors. Optimized for older hardware and/or Vulkan acceleration. Fits 131K context on 24GB depending on cache quantization levels and whether vision is…
Downloads · 30 days
27
7% of all-time downloads
All-time downloads
389
Public
Repo size
17 GB
Likes
1
Public
Click a slice to open those files.
.gguf17 GB · 100%
From the Hugging Face model README
Qwen3.6-27B-smol-MTP-IQ4_NL from ubergarm with grafted MTP/draft tensors. Optimized for older hardware and/or Vulkan acceleration. Fits 131K context on 24GB depending on cache quantization levels and whether vision is loaded on GPU or not.