Uncensored Gemma 4 E4B & E2B (0/465 refusals) with MTP drafter. 32k context, up to 80 TPS on RTX 3050 8GB.

vision tools thinking

ollama run s1gnature/gemma4-uncensored-mtp:e2b-q4_k_m

curl http://localhost:11434/api/chat \
  -d '{
    "model": "s1gnature/gemma4-uncensored-mtp:e2b-q4_k_m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='s1gnature/gemma4-uncensored-mtp:e2b-q4_k_m',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 's1gnature/gemma4-uncensored-mtp:e2b-q4_k_m',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model s1gnature/gemma4-uncensored-mtp:e2b-q4_k_m

OpenCode ollama launch opencode --model s1gnature/gemma4-uncensored-mtp:e2b-q4_k_m

Hermes Agent ollama launch hermes --model s1gnature/gemma4-uncensored-mtp:e2b-q4_k_m

OpenClaw ollama launch openclaw --model s1gnature/gemma4-uncensored-mtp:e2b-q4_k_m

Models

View all →

Name

3 models

Size / Usage

Context

Input

gemma4-uncensored-mtp:e2b-q4_k_m

3.6GB · 128K context window · Text · 4 days ago

gemma4-uncensored-mtp:e2b-q4_k_m

3.6GB

128K

Text

gemma4-uncensored-mtp:e2b-q8_0

5.1GB · 128K context window · Text · 4 days ago

gemma4-uncensored-mtp:e2b-q8_0

5.1GB

128K

Text

gemma4-uncensored-mtp:e4b-q4_k_m

6.5GB · 128K context window · Text, Image · 4 days ago

gemma4-uncensored-mtp:e4b-q4_k_m

6.5GB

128K

Text, Image

Readme

Gemma 4 E4B & E2B Uncensored MTP (Q4_K_M)

Uncensored builds of Gemma 4 E4B & E2B with MTP drafter.

Specs

Quantizations: Q4_K_M, Q8_0
Context length: 32,000 tokens
Speed: Up to 80 TPS on RTX 3050 8GB OC
Refusals: 0/465 refusals

Credits

Base model: HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
MTP module: matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF