igorls/gemma4-e4b-classifier

igorls/ gemma4-e4b-classifier

323 Downloads Updated 3 months ago

A modality-stripped variant of google/gemma-4-E4B-it for text-only classification, entity extraction, and structured-memory extraction. The vision encoder (150M params) and audio encoder (300M params) are removed; the text path is unchanged.

tools thinking

ollama run igorls/gemma4-e4b-classifier

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

from ollama import chat

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

import ollama from 'ollama'

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

Applications

Claude Code ollama launch claude --model igorls/gemma4-e4b-classifier

OpenCode ollama launch opencode --model igorls/gemma4-e4b-classifier

Hermes Agent ollama launch hermes --model igorls/gemma4-e4b-classifier

OpenClaw ollama launch openclaw --model igorls/gemma4-e4b-classifier

Models

View all →

Name

3 models

Size / Usage

Context

Input

gemma4-e4b-classifier:latest

5.3GB · 128K context window · Text · 3 months ago

gemma4-e4b-classifier:latest

5.3GB

128K

Text

gemma4-e4b-classifier:Q4_K_M

5.3GB · 128K context window · Text · 3 months ago

gemma4-e4b-classifier:Q4_K_M

5.3GB

128K

Text

gemma4-e4b-classifier:Q8_0

8.0GB · 128K context window · Text · 3 months ago

gemma4-e4b-classifier:Q8_0

8.0GB

128K

Text

Readme

No readme