Unsloth Gemma 4 26B GGUF
Optimized, quantized GGUF versions of Google's Gemma 4 26B model for local inference.
huggingface.coBuilt with
UnknownBuild evidence
Strong
This is an official model distribution page on Hugging Face hosted by the Unsloth organization.
Creator
Unsloth AI @unslothShipped
1h agoThese quantized GGUF format weights of the Gemma 4 26B MoE model are optimized by Unsloth for efficient local inference across various hardware setups. They enable users to run large-scale open models on consumer-grade hardware with support for standard libraries like llama.cpp and vLLM.
Timeline
Teaser
Video
Playable
Product
Loading…
