Downloads · 30 days
296
3% of all-time downloads
elpirater312/nohurry-gemma-4-26B-A4B-it-heretic-IQ4_NL-ud-imtrx-GUFF
nohurry-gemma-4-26B-A4B-it-heretic-IQ4_NL-ud-imtrx-GUFF is a machine learning model from elpirater312. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
The previous version was built on outdated llama.cpp kernels. This V2 release incorporates the latest architectural fixes for Gemma-4, including the <unused24 buffer fix and Logit Soft-Capping.
Downloads · 30 days
296
3% of all-time downloads
All-time downloads
9.2K
Public
Repo size
29.2 GB
Likes
6
Public
Click a slice to open those files.
.gguf29.2 GB · 100%
From the Hugging Face model README
The previous version was built on outdated llama.cpp kernels. This V2 release incorporates the latest architectural fixes for Gemma-4, including the <unused24> buffer fix and Logit Soft-Capping.
The previous quant is out of date and MISSING critical architectural fixes. This V2 release is the first to incorporate the Unsloth Dynamic 2.0 re-computed imatrix and the latest llama.cpp Gemma-4 patches.
<unused24> token buffer overlap fixed (No more random logic crashes).add_bos now defaults to True for native Gemma-4 behavior.final_logit_softcapping (CRITICAL for preventing NaN/Infinity loops).IQ4_NL (Non-Linear) - Higher logic-per-bit than Q4_K_M or Q4_0.Q8_0 Token Embeddings and Output Head (Prevents vocabulary degradation).All credits to Merijn Hendriks (nohurry) for the heretic weights and Unsloth for the imatrix file.