kwangsuklee/gemma4-e4b-abliterated-Q8

kwangsuklee/ gemma4-e4b-abliterated-Q8:latest

137 Downloads Updated 2 days ago

huggingface.co/Jiunsong/supergemma4-e4b-abliterated

tools thinking

ollama run kwangsuklee/gemma4-e4b-abliterated-Q8

curl http://localhost:11434/api/chat \
  -d '{
    "model": "kwangsuklee/gemma4-e4b-abliterated-Q8",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='kwangsuklee/gemma4-e4b-abliterated-Q8',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'kwangsuklee/gemma4-e4b-abliterated-Q8',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 days ago

2 days ago

5248fddd1548 · 8.0GB ·

model

archgemma4

parameters7.52B

quantizationQ8_0

8.0GB

params

{ "stop": [ "<turn|>" ], "temperature": 1, "top_k": 64, "top_p": 0.95 }

71B

Readme

https://ollama.com/library/gemma4:e4b

https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated

SuperGemma4 E4B Abliterated supergemma4-e4b-abliterated is a private evaluation release whose original upstream base is google/gemma-4-E4B-it.

This SuperGemma release is an abliterated and tuned derivative of that Google E4B base, with additional work for higher release quality, stronger formatting discipline, better code output, and faster time to first token.

This branch is aimed at users who want:

strong code and bug-fix behavior clean JSON and tool-call formatting fast first-token responsiveness release-ready serving behavior on Transformers and OpenAI-compatible stacks

Ref. https://ollama.com/0xIbra/supergemma4-26b-uncensored-gguf-v2:Q4_K_M https://huggingface.co/Jiunsong/supergemma4-26b-uncensored-gguf-v2