Downloads · 30 days
0
VeigaPunk/gemma4-26b-hvm4
gemma4-26b-hvm4 is a text generation model from VeigaPunk. Use it when you need the model to write or continue text. It is set up for ollama. The card lists the license as gemma.
Control-plane adapter for running the Gemma 4 26B A4B model through Bend 0.2.38 and HVM4 4.0.x before local Ollama inference.
Downloads · 30 days
0
Access
Public
Updated Jul 22, 2026
Repo size
—
Likes
0
Public
Click a slice to open those files.
.sh8.4 KB · 60%
From the Hugging Face model README
Control-plane adapter for running the Gemma 4 26B A4B model through Bend 0.2.38 and HVM4 4.0.x before local Ollama inference.
prompt → Bend control generation → HVM4 control execution → Ollama/Gemma 4
HVM4 performs bounded pure control computation; model tensor inference remains in Ollama. This repository does not claim that Gemma tensor operations execute inside HVM4.
The included Ollama Modelfile derives from gemma4:26b and creates the local gemma4:26b-hvm4 lane.
ollama create gemma4:26b-hvm4 -f hvm4/Modelfile.26b-hvm4
HVM_GEMMA_MODEL=gemma4:26b-hvm4 ./run-hvm4.sh "Reply exactly: HVM4_OK"
-C1gemma4:26b-hvm4run-hvm4.sh: validated HVM4/Ollama runnerhvm4/Main.hs: Haskell adapterhvm4/mailbox.bend: Bend2 mailbox classifier sourcehvm4/mailbox-bend2.sh: mailbox substrate entrypointhvm4/Modelfile.26b-hvm4: Ollama model definitionModel usage remains subject to the Gemma Terms of Use. Adapter code follows the companion project license.